Paper Citation Record · LEDGER

Monet: Mixture of Monosemantic Experts for Transformers

As of 14 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 2 inbound Pith citation observations for arXiv:2412.04139.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.04139 v4

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T21:49:17.483517Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:55:02.197434Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-09T12:08:23.021613Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy17
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 48ae1320-e6a8-437e-ac3a-4fed29d17f1b · outbound

This paper cites Nemotron-4 340B Technical Report.

Monet: Mixture of Monosemantic Experts for Transformers Nemotron-4 340B Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.305101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b05858b-9258-499a-bb95-2cdf3134d911 · outbound

This paper cites b", nn.initializers.zeros, b_shape) 11 12def call(self, x, g1, g2): 13x = nn.relu(self.u(x)) ** 2 14x = jnp.einsum(.

Monet: Mixture of Monosemantic Experts for Transformers b", nn.initializers.zeros, b_shape) 11 12def __call__(self, x, g1, g2): 13x = nn.relu(self.u(x)) ** 2 14x = jnp.einsum(

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.015573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f52d3f37-a5a4-4a4a-976d-58e3e238cf44 · outbound

This paper cites Haozhe Chen, Carl V ondrick, and Chengzhi Mao.

Monet: Mixture of Monosemantic Experts for Transformers Haozhe Chen, Carl V ondrick, and Chengzhi Mao

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.319506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3bd332f-a45c-490c-81c8-a25fd29239de · outbound

This paper cites Fkyou!Fk (...)* (16.68%)(...)Snakesonamotherf*ckingplane.

Monet: Mixture of Monosemantic Experts for Transformers F**kyou!F**k (...)* (16.68%)(...)Snakesonamotherf*ckingplane

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:17.904732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cb4d296f-f8ed-4751-80d6-5f80c23a81c6 · outbound

This paper cites RealToxi- cityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

Monet: Mixture of Monosemantic Experts for Transformers RealToxi- cityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.103123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 50b5e7a9-de52-495d-b6ee-ae6976f0760c · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Monet: Mixture of Monosemantic Experts for Transformers Transformer Feed-Forward Layers Are Key-Value Memories

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.092077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 079ff9d5-2989-4396-b146-5c1b7bf9854e · outbound

This paper cites Mixture of A Million Experts.

Monet: Mixture of Monosemantic Experts for Transformers Mixture of A Million Experts

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.345568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7be31826-7cc4-468c-832e-0eaaf53d73fc · outbound

This paper cites An Overview of Catastrophic AI Risks.

Monet: Mixture of Monosemantic Experts for Transformers An Overview of Catastrophic AI Risks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.350721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 282fbb42-89ca-4431-92a4-f850a48bdc8d · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Monet: Mixture of Monosemantic Experts for Transformers AI Alignment: A Comprehensive Survey

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.355345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d396f3-f03a-4a46-8b79-f4fe4f2aae47 · outbound

This paper cites Mixtral of Experts.

Monet: Mixture of Monosemantic Experts for Transformers Mixtral of Experts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.359959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5837cd5c-81c5-4297-9768-8331a34d6c41 · outbound

This paper cites The Stack: 3 TB of permissively licensed source code.

Monet: Mixture of Monosemantic Experts for Transformers The Stack: 3 TB of permissively licensed source code

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.366448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c909ed0d-cae8-4be6-a2ea-195e35dfac81 · outbound

This paper cites Theory on Mixture-of-Experts in Continual Learning.

Monet: Mixture of Monosemantic Experts for Transformers Theory on Mixture-of-Experts in Continual Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.372648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09b0c3ed-ca01-4bd2-b729-05e8f79176b7 · outbound

This paper cites StarCoder: may the source be with you!.

Monet: Mixture of Monosemantic Experts for Transformers StarCoder: may the source be with you!

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.377588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f7b35d-b5d2-4d89-b75d-2b9c9eed1692 · outbound

This paper cites Scaling Laws for Fine-Grained Mixture of Experts.

Monet: Mixture of Monosemantic Experts for Transformers Scaling Laws for Fine-Grained Mixture of Experts

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.080870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 27bd9235-fb72-459e-ac69-e41d5c8db21b · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Monet: Mixture of Monosemantic Experts for Transformers Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.386441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec5e0d1f-8b6d-4135-a950-e7c1c5844321 · outbound

This paper cites Jesse Mu and Jacob Andreas.

Monet: Mixture of Monosemantic Experts for Transformers Jesse Mu and Jacob Andreas

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.066925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e650a4d8-dfe9-47c6-b120-9261da758d87 · outbound

This paper cites OLMoE: Open Mixture-of-Experts Language Models.

Monet: Mixture of Monosemantic Experts for Transformers OLMoE: Open Mixture-of-Experts Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.396208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17cd2fc4-25f7-46dc-b552-0baf645a894d · outbound

This paper cites Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models.

Monet: Mixture of Monosemantic Experts for Transformers Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.400132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aefa3d9c-84a0-4219-83bf-2b3f5d689843 · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

Monet: Mixture of Monosemantic Experts for Transformers The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.404980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa7fe330-0eaf-4015-bae2-c6511e5a16a9 · outbound

This paper cites Taking features out of superposition with sparse autoencoders.

Monet: Mixture of Monosemantic Experts for Transformers Taking features out of superposition with sparse autoencoders

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.053942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8cb3b353-fb27-4997-a56f-98bdb79ee9c0 · outbound

This paper cites JetMoE: Reaching Llama2 Performance with 0.1M Dollars.

Monet: Mixture of Monosemantic Experts for Transformers JetMoE: Reaching Llama2 Performance with 0.1M Dollars

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.414775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc2d541-93b0-4641-9cde-bbe132a9a1b0 · outbound

This paper cites Codebook Features: Sparse and Discrete Interpretability for Neural Networks.

Monet: Mixture of Monosemantic Experts for Transformers Codebook Features: Sparse and Discrete Interpretability for Neural Networks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.418586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e7dff76-7ce8-4d30-b7f3-bfae6a2551ac · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Monet: Mixture of Monosemantic Experts for Transformers Gemma 2: Improving Open Language Models at a Practical Size

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.422409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c0a478-58f3-4a12-b0dd-135ab96bcabe · outbound

This paper cites ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs.

Monet: Mixture of Monosemantic Experts for Transformers ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.426665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88ddfaba-7cce-45f2-ab6d-bcace9afc643 · outbound

This paper cites CONTENTS A Method Descriptions 18 A.1 Expansion of Vertical Decomposition.

Monet: Mixture of Monosemantic Experts for Transformers CONTENTS A Method Descriptions 18 A.1 Expansion of Vertical Decomposition

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.042704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5787dd54-254f-43b2-bf12-6405cace9c38 · outbound

This paper cites Moreover, the multi-head expert routing probabilities are consoli- dated into single routing coefficients PH h=1 ˆg1 hi and PH h=1 ˆg2 hj, reducing redundant aggregations.

Monet: Mixture of Monosemantic Experts for Transformers Moreover, the multi-head expert routing probabilities are consoli- dated into single routing coefficients PH h=1 ˆg1 hi and PH h=1 ˆg2 hj, reducing redundant aggregations

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.030720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b521dc35-7029-4b51-819d-64fea07fada6 · outbound

This paper cites an unresolved cited work.

Monet: Mixture of Monosemantic Experts for Transformers Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:49:18.001376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 205d08a4-c02a-4e40-9b3f-dce2b2e89ee2 · outbound

This paper cites b1", nn.initializers.zeros, b_shape) 16self.b2 = self.param(.

Monet: Mixture of Monosemantic Experts for Transformers b1", nn.initializers.zeros, b_shape) 16self.b2 = self.param(

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:17.987633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2155c7b8-ccad-4b50-88cc-fd5497bd2339 · outbound

This paper cites To manage computational resources effectively, we adopt a group routing strategy wherein the routing probabilities are reused every 4 layers.

Monet: Mixture of Monosemantic Experts for Transformers To manage computational resources effectively, we adopt a group routing strategy wherein the routing probabilities are reused every 4 layers

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:17.972085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3b6d7aa3-ec52-4887-8481-d7afdbb26e34 · outbound

This paper cites an unresolved cited work.

Monet: Mixture of Monosemantic Experts for Transformers Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:49:17.958821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d3aad49d-4168-44ca-8d6c-53e51176b194 · outbound

This paper cites The ta- ble reports the number of experts assigned to each programming language across all routing groups.

Monet: Mixture of Monosemantic Experts for Transformers The ta- ble reports the number of experts assigned to each programming language across all routing groups

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:17.945417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f0ad5e76-b44c-44e2-acc1-27ddb37e82c7 · outbound

This paper cites "" 12#!/usr/bin/env bash 13 14echo.

Monet: Mixture of Monosemantic Experts for Transformers "" 12#!/usr/bin/env bash 13 14echo

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:17.931920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 248b5d53-cb14-42fb-a7cf-2921df6104fa · outbound

This paper cites Based on this, we masked experts associated with each language and re-evaluated the code generation benchmark to estimate the model’s capa- bility to unlearn programming languages.

Monet: Mixture of Monosemantic Experts for Transformers Based on this, we masked experts associated with each language and re-evaluated the code generation benchmark to estimate the model’s capa- bility to unlearn programming languages

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:17.918495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ff23ca77-efa7-4ac1-896b-d436f02b129c · outbound

This paper cites JULYIV (...)rew (59.50%)(...)TheembroideryreadsinHebrew:.

Monet: Mixture of Monosemantic Experts for Transformers JULYIV (...)rew (59.50%)(...)TheembroideryreadsinHebrew:

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:17.890678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5dfbb1be-ff90-4064-873d-92e3824017e8 · outbound

This paper cites BatchTopK: A Simple Improvement for TopK- SAEs.AI Alignment F orum,.

Monet: Mixture of Monosemantic Experts for Transformers BatchTopK: A Simple Improvement for TopK- SAEs.AI Alignment F orum,

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.126943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3be18078-dc49-4ee3-8d8c-5a5a606dd494 · outbound

This paper cites Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models.

Monet: Mixture of Monosemantic Experts for Transformers Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.340410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38440118-84ef-488e-9c34-51d3bc740853 · outbound

This paper cites A Review of Sparse Expert Models in Deep Learning.

Monet: Mixture of Monosemantic Experts for Transformers A Review of Sparse Expert Models in Deep Learning

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T21:49:17.328429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f391b43e-99f7-4df1-b0be-83ca33bcbf8c · outbound

This paper cites an unresolved cited work.

Monet: Mixture of Monosemantic Experts for Transformers Unresolved cited work

Reference 2023

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:49:18.140201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a2481438-38c2-41c0-b057-1993764de5aa · outbound

This paper cites Mem- ory Augmented Language Models through Mixture of Word Experts.

Monet: Mixture of Monosemantic Experts for Transformers Mem- ory Augmented Language Models through Mixture of Word Experts

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:49:18.114743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation e3e18910-6f01-4337-ad66-3b0d06010f01 · inbound

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition cites this paper.

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Monet: Mixture of Monosemantic Experts for Transformers

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-10T14:55:02.197434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9802ffa-0cfa-4a99-b7e6-efa79ea705d1 · inbound

Studying Cross-cluster Modularity in Neural Networks cites this paper.

Studying Cross-cluster Modularity in Neural Networks Monet: Mixture of Monosemantic Experts for Transformers

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:08:23.058043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.