Verbal confidence in LLMs tracks future commit/abstain decisions more than answer correctness, while log-probabilities track correctness.
super hub Mixed citations
Steering Language Models With Activation Engineering
Mixed citation behavior. Most common role is background (62%).
164
Pith papers citing it
Background
62% of classified citations
abstract
Prompt engineering and finetuning aim to maximize language model performance on a given metric (like toxicity reduction). However, these methods do not fully elicit a model's capabilities. To reduce this gap, we introduce activation engineering: the inference-time modification of activations in order to control (or steer) model outputs. Specifically, we introduce the Activation Addition (ActAdd) technique, which contrasts the intermediate activations on prompt pairs (such as "Love" versus "Hate") to compute a steering vector (Subramani et al. 2022). By tactically adding in e.g. the "Love" - "Hate" steering vector during the forward pass, we achieve SOTA on negative-to-positive sentiment shift and detoxification using models including LLaMA-3 and OPT. ActAdd yields inference-time control over high-level output properties (like topic and sentiment) while preserving performance on off-target tasks. ActAdd is lightweight: it does not require any machine optimization and works with a single pair of data points, which enables rapid iteration over steering. ActAdd demonstrates the power of activation engineering.
hub tools
citation-role summary
background 16
baseline 2
method 2
dataset 1
citation-polarity summary
claims ledger
- abstract Prompt engineering and finetuning aim to maximize language model performance on a given metric (like toxicity reduction). However, these methods do not fully elicit a model's capabilities. To reduce this gap, we introduce activation engineering: the inference-time modification of activations in order to control (or steer) model outputs. Specifically, we introduce the Activation Addition (ActAdd) technique, which contrasts the intermediate activations on prompt pairs (such as "Love" versus "Hate") to compute a steering vector (Subramani et al. 2022). By tactically adding in e.g. the "Love" - "H
authors
co-cited works
representative citing papers
WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.
SLAM achieves 100% detection on Gemma-2 models with only 1-2 point quality cost by causally steering SAE-identified residual-stream directions for linguistic structure.
LLMs compute Nash actions internally but suppress them via prosocial overrides from training data, and this can be causally controlled through residual stream interventions.
LLM activations encode current and prior entities in orthogonal slots, but models only use the current slot for explicit factual retrieval despite prior-slot information being linearly decodable.
Function vectors steer LLMs successfully where the logit lens fails to decode the target answer, showing the two properties come apart.
Knowledge Packs deliver knowledge via pre-computed KV caches with exact equivalence under causal masking, achieving zero divergences on tested questions and enabling value-based steering without training.
Linear representations of high-level concepts in LLMs are formalized via counterfactuals in input and output spaces, unified under a causal inner product that enables consistent probing and steering.
Response-time linear probing on first generated tokens detects prefilling attacks missed by prompt-time activation defenses, achieving 0/40 attack success and 0% false positives across seven models while composing orthogonally with AlphaSteer.
Rotate2Think estimates an orthogonal rotation from input to thinking embeddings via Procrustes analysis on a few examples and injects the resulting vector to prime reasoning traces, raising accuracy in 30 of 32 model-benchmark settings.
A geometric decomposition framework shows that affine transformations best recover prompt-induced task geometry and behavior in language and vision models across multiple datasets.
Subliminal learning is steering vector distillation: a student fine-tuned on a steered teacher's outputs learns to imitate the steering vector.
ACROS induces explicit sense representations in frozen decoder LMs via gated residual addition, enabling competitive zero-shot WSD, lexical steering, and cross-lingual adaptation on SmolLM2-360M while preserving base quality.
Transformer Field Theory frames the residual stream as a field, models patching as source insertion, and uses first-order sensitivities plus Green functions to predict and describe responses, with empirical tests on GPT-2 autoregressive models.
A Riemannian geodesic framework for label-free manifold steering in language models via a schema-supervised encoder approximating output Hellinger distance on activations.
Introduces a template-controlled difference-in-differences protocol that corrects chat-template confounding when measuring alignment-induced activation shifts in LLMs and recovers the refusal direction with higher fidelity.
Transformers trained from different random seeds exhibit residual-stream polymorphism that is exactly a uniform random rotation, which a Procrustes alignment removes to transfer SAEs and steering vectors.
ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
Persona and task in role prompts decompose additively into orthogonal directions at the prompt-to-answer transition in LLM residual streams, but this local structure does not allow compressing the prompt into a single cached residual vector because generation depends on distributed attention to the原
VerifySteer selectively steers hidden states at paragraph boundaries using latent correctness signals to control verifier strictness and outperform baselines on ProcessBench and Hard2Verify with lower compute.
Residual Paving decomposes selective refusal editing into an early-layer router for intervention decisions and later-layer residual experts for edits, with oracle routing showing that learned route selectivity is the primary bottleneck across six backbones.
FishBack derives a closed-form minimum-distortion steering direction from the pullback Fisher metric of the softmax layer, outperforming Euclidean baselines on GPT-2 verb-morphology tasks with lower off-target KL divergence.
Pretraining and alignment induce asymmetric geometric traces in transformer weights because alignment updates concentrate in read pathways due to activation covariance while write pathways inherit less structure from alignment losses.
In two-layer networks, weak-to-strong training elicits the target feature direction from pre-trained subspaces and preserves correlated off-target features, unlike standard fine-tuning.
citing papers explorer
-
The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
In two-layer networks, weak-to-strong training elicits the target feature direction from pre-trained subspaces and preserves correlated off-target features, unlike standard fine-tuning.
-
Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning
Spurious latent factors in fine-tuning can be identified unsupervised from naive LoRA weights and removed via gradient projection of associated patterns to reduce bias and misalignment while preserving task performance.