Centered Ablation: Why Last-Layer Directional Ablation Under-Fires or Collapses, and a Closed-Form Fix
Organizations: Knovel Engineering Lab, Singapore
Abstract
Directional ablation removes a hidden state's component along a "behaviour direction" while a language model runs. It is the standard way to switch a behaviour such as refusal off, but it is erratic: on some models it barely fires, on others the text collapses into repetition. We show why, and fix it. At the last residual stream, ablation is exactly a logit bias: a fixed vocabulary footprint scaled by a gate, the cosine between the hidden state and the direction. The gate is measured from the origin, but last-layer states share a large common mode far from it, so a direction that overlaps the common mode fires on benign text and under-fires on its targets. Centered Ablation (CA) projects the common mode out of the direction, in closed form. Across 8 models, CA raises attack success by 29 and 46 points where the standard recipe under-fires, cuts collapse on Gemma-2-9B from 50% to 1%, and preserves 12 to 40 points more benign answers on high-overlap models, 39 to 46 more than the affine offset of prior work. Two numbers computed before generation predict, on models the analysis had not seen, which gain faithfulness and which gain attack success, and a collapse index marks when text degenerates. We also show that two standard safety judges score collapsed text in opposite directions, which can fabricate a 46-point effect.
Figures & tables
| Closed form | Centred gate | Exact effect | Predicts in advance | Explains collapse | |
| Activation addition, CAA | ✓ | – | – | – | – |
| Directional ablation (DIM) | ✓ | – | – | – | – |
| ACE (affine offset) | ✓ | ✓ | – | – | – |
| Erasure (INLP, LEACE) | ✓ | – | – | – | – |
| Conditional steering (CAST) | – | – | – | – | – |
| CA (ours) | ✓ | ✓ | ✓ | ✓ | ✓ |
Appendix figures & tables26 assets
Supplementary material from the paper’s appendix.
Appendix
| Term | Meaning | Defined |
| Methods and conditions | ||
| directional ablation | remove a hidden state’s component along a direction while the model runs | Equation 2 |
| DIM, DIM ablation | the standard recipe: ablation along the difference-in-means direction | Section 3.1 |
| CA, Centered Ablation | ours: ablation along DIM with the benign common mode projected out | Equation 7 |
| DIM+offset (offset route) | DIM ablation with the gate re-anchored at the benign mean by an offset; ACE’s affine correction at our site | Equation 8 |
| ACE | affine concept editing ( Marshall et al., 2025 ) , the prior method whose offset DIM+offset uses | Section 2 |
| Symbol | Meaning | Defined |
| The model’s output head | ||
| residual stream after the last of decoder blocks, at one token position | Section 3.1 | |
| , , | final RMSNorm , its diagonal gain, and | Equation 1 |
| , | unembedding matrix, vocabulary size | Equation 1 |
| logits (pre-cap for Gemma-2; see A2) | Equation 1 | |
| , | ; , the coefficient of along | here |
| Model | Family | Entered | ||||
| Qwen2.5-0.5B-Instruct | Qwen | 896 | 24 | .022 | .679 | after the pilot |
| Qwen3-4B-Instruct-2507 | Qwen | 2560 | 36 | .034 | .963 | after the pilot |
| Qwen2.5-7B-Instruct | Qwen | 3584 | 28 | .041 | .888 | pilot |
| Qwen2.5-3B-Instruct | Qwen | 2048 | 36 | .125 | .921 | after the pilot |
| Gemma-2-2B-it | Gemma | 2304 | 26 | .315 | .979 | after the pilot |
| Llama-3.1-8B-Instruct | Llama | 4096 | 32 | .332 | .458 | pilot |
| Role | Source | Size |
| harmful calibration | AdvBench ( Zou et al., 2023b ) | 256 per draw from 416 |
| benign calibration | Alpaca instructions ( Taori et al., 2023 ) | 256 per draw from 416 |
| attack evaluation | HarmBench test, copyright split removed ( Mazeika et al., 2024 ) | 240 |
| benign evaluation | Alpaca held-out | 100 |
| jailbreak evaluation | JailbreakBench behaviours ( Chao et al., 2024 ) 8 templates (train: prefix-injection, refusal-suppression, fiction, AIM; held out: dev-mode, research, evil-confidant, few-shot-compliance) | 100 per template |
| over-refusal | XSTest safe prompts ( Röttger et al., 2024 ) ; JailbreakBench benign | 250; 100 |
| Setting | Value |
|---|---|
| Calibration | |
| states | residual stream after the last block, at the last prompt token, chat template applied |
| calibration size | 256 harmful (AdvBench) and 256 benign (Alpaca) prompts per draw |
| calibration draws | 6; draw 0 is a fixed split with shuffle seed 42, draws 1–5 resample 256 of each pool excluding the Alpaca evaluation slice |
| DIM+offset offset | on the same 256 benign calibration states (prompt-final) |
| Steering and generation | |
| Metric | Judge | Prompt | Calls |
| ASR (HB) | HarmBench classifier | P1 | one per generation |
| ASR (LG) | Llama-Guard-3-8B | its built-in chat template, no custom prompt | one per generation |
| pairwise quality | Qwen3-8B | P2 | two per answer (both orders) |
| emotion label | Qwen3-8B | P3 | one per story |
| keyword refusal | none | prefix list ( Table 8 ) | – |
| Refusal prefixes |
| I’m sorry; I am sorry; I apologize; As an AI; As a language model; I cannot; I can’t (straight and curly apostrophe); I’m unable; I am unable; I will not; I won’t; I’m not able; I must decline; I’m not going to; Sorry; I do not; cannot fulfill; can’t help; cannot help; not able to provide |
| Model | Agreement (%) |
| Qwen2.5-7B | 99.9 |
| Qwen3-4B | 99.2 |
| Gemma-2-2B | 98.8 |
| Llama-3.1-8B | 98.5 |
| Llama-3.2-3B | 97.5 |
| Qwen2.5-0.5B | 96.7 |
| Model | Direction | HB | HB-F | LG | LG-F | collapse |
| Qwen2.5-0.5B | none | 23.8 | 23.8 | 34.2 | 34.2 | 0 |
| DIM | 51.1 2.0 | 49.7 | 80.7 1.2 | 77.8 | 3 | |
| DIM+offset | 50.9 1.2 | 49.7 | 82.6 1.1 | 79.6 | 3 | |
| CA | 51.0 1.8 | 49.7 | 81.9 0.9 | 78.8 | 3 | |
| Qwen3-4B | none | 2.1 | 2.1 | 0.8 | 0.8 | 0 |
| DIM | 7.4 0.4 | 7.4 | 9.5 0.9 | 9.5 | 0 |
| Model | CA DIM HB-F | McN | CA DIM LG-F | McN | CA DIM+offset HB-F | CA DIM+offset LG-F |
| Qwen2.5-0.5B | +0.0 [-2.1, +2.2] | 0/6 | +1.0 [-0.6, +2.7] | 0/6 | -0.1 [-2.2, +2.0] | -0.8 [-2.2, +0.6] |
| Qwen3-4B | -0.3 [-0.8, +0.2] | 0/6 | -0.4 [-1.5, +0.6] | 0/6 | -0.4 [-1.3, +0.3] | -1.5 [-2.8, -0.2] |
| Qwen2.5-7B | -2.2 [-4.3, +0.0] | 0/6 | -3.0 [-5.2, -0.9] | 1/6 | -3.7 [-6.8, -0.7] | -4.6 [-7.2, -1.9] |
| Qwen2.5-3B | +2.4 [-0.8, +5.5] | 0/6 | +3.5 [+0.2, +6.7] | 1/6 | -12.4 [-16.6, -8.3] | -11.3 [-15.1, -7.5] |
| Gemma-2-2B | -2.6 [-6.9, +1.7] | 0/6 | -11.2 [-15.8, -6.5] | 6/6 | -0.5 [-4.2, +3.3] | +4.4 [+0.6, +8.1] |
| Llama-3.1-8B | +29.0 [+22.9, +35.1] | 6/6 | +33.6 [+27.3, +39.8] | 6/6 | -2.9 [-7.2, +1.6] | -5.5 [-10.1, -0.8] |
| Model | DIM | DIM+offset | CA | DIM CA | DIM+offset CA | |
| Qwen2.5-0.5B | .022 | 59.2 | 60.7 | 60.0 | -0.8 | +0.7 |
| Qwen3-4B | .034 | 30.2 | 29.5 | 30.3 | -0.2 | -0.8 |
| Qwen2.5-7B | .041 | 35.2 | 41.0 | 33.8 | +1.3 | +7.2 |
| Qwen2.5-3B | .125 | 67.5 | 55.0 | 62.8 | +4.7 | -7.8 |
| Gemma-2-2B | .315 | 87.5 | 69.7 | 71.0 | +16.5 | -1.3 |
| Llama-3.1-8B | .332 | 45.8 | 72.8 | 33.5 | +12.3 | +39.3 |
| Model | unsteered | DIM | DIM+offset | CA |
| Qwen2.5-0.5B | 43.5 | 42.8 | 43.1 | 43.0 |
| Qwen3-4B | 67.9 | 68.0 | 68.0 | 68.0 |
| Qwen2.5-7B | 71.5 | 71.4 | 71.4 | 71.4 |
| Qwen2.5-3B | 61.1 | 60.9 | 61.2 | 60.9 |
| Gemma-2-2B | 56.4 | 57.1 | 56.4 | 56.6 |
| Llama-3.1-8B | 64.0 | 64.0 | 63.9 | 63.8 |
| Model | DIM | DIM+offset | CA | ties (%) |
| Qwen2.5-0.5B | +1.5 | +4.0 | +1.5 | 70–72 |
| Qwen3-4B | +9.5 | +7.0 | +7.0 | 84–86 |
| Qwen2.5-7B | +2.5 | -2.0 | +3.5 | 84–88 |
| Qwen2.5-3B | -5.5 | +1.5 | -5.0 | 78–85 |
| Gemma-2-2B | +0.5 | -6.0 | +4.5 | 78–82 |
| Llama-3.1-8B | -10.0 | +3.0 | -4.0 | 81–83 |
| Model | ratio predicted | ratio measured | benign sd DIM+offset | benign sd CA | ASR DIM+offset CA | rewrites DIM+offset CA | ||
| Qwen2.5-0.5B | .022 | 1.000 | 1.002 | .078 | .078 | 1.0 | +0.1 | +0.7 |
| Qwen3-4B | .034 | 1.001 | 1.001 | .091 | .092 | 0.8 | +0.4 | -0.8 |
| Qwen2.5-7B | .041 | 1.001 | 1.000 | .050 | .052 | 8.5 | +3.7 | +7.2 |
| Qwen2.5-3B | .125 | 1.008 | 1.010 | .061 | .059 | 4.0 | +12.4 | -7.8 |
| Gemma-2-2B | .315 | 1.054 | 1.063 | .074 | .053 | 5.5 | +0.5 | -1.3 |
| Llama-3.1-8B | .332 | 1.060 | 1.047 | .061 | .051 | 3.2 | +2.9 | +39.3 |
| Model | regime | benign change (%) | harmful change (%) | preserved | ASR gain | ||
| Qwen2.5-0.5B | .022 | .679 | no-op | 12.5 13.1 | 67.9 70.0 | -0.8 | -0.1 |
| Qwen3-4B | .034 | .963 | no-op | 4.4 3.1 | 96.3 96.3 | -0.2 | -0.3 |
| Qwen2.5-3B | .125 | .921 | no-op | 8.1 5.0 | 92.1 95.0 | +4.7 | +2.4 |
| Gemma-2-2B | .315 | .979 | gate-gain | 26.3 4.4 | 97.9 96.3 | +16.5 | -2.6 |
| Llama-3.2-3B | .438 | .083 | collapse-fix | 25.0 5.6 | 8.3 78.8 | +18.5 | +46.3 |
| Model | DIM | DIM+offset | CA | collapse DIM CA | |
| Qwen2.5-0.5B | .022 | .293 / .058 | .306 / .058 | .305 / .058 | 3 3 |
| Qwen3-4B | .034 | .569 / .060 | .586 / .055 | .587 / .055 | 0 0 |
| Qwen2.5-7B | .041 | .470 / .041 | .495 / .035 | .496 / .037 | 0 0 |
| Qwen2.5-3B | .125 | .422 / .082 | .505 / .041 | .499 / .039 | 0 0 |
| Gemma-2-2B | .315 | .895 / .370 | .545 / .069 | .563 / .051 | 1 0 |
| Llama-3.1-8B | .332 | .415 / .191 | .629 / .041 | .586 / .032 | 0 0 |
| Model | Gate / | Suppressed | Promoted |
| Qwen2.5-7B | .53 / .02 | I, Sorry | Sure |
| Llama-3.1-8B | .43 / .21 | I, cannot | Here, The |
| Gemma-2-9B | .68 / .44 | I, immoral | AnchorStyles , EconPapers |
| Direction | ASR / collapse rate | ||
| Qwen2.5-7B | Llama-3.1-8B | Gemma-2-9B | |
| unsteered | 11.7 / 0 | 9.2 / 0 | 2.1 / 0 |
| random direction | 12.5 / 0 | 11.2 / 0 | 2.1 / 0 |
| DIM | 51.2 / 0 | 32.1 / 0 | 15.4 / 50 |
| length-reweighted DIM fixed point | 42.9 / 0 | 63.7 / 0 | 19.6 / 18 |
| MMD erasure, linear kernel, with | 39.2 / 0 | 63.7 / 0 | 13.8 / 2 |
| Qwen2.5-7B | Llama-3.1-8B | Gemma-2-9B | |
| .87 | .83 | .99 | |
| .15 | .22 | .11 | |
| .99 | .99 | .92 | |
| top-10 coordinates’ share of mean-vector energy | 35% | 13% | 88% |
| .041 | .332 | .471 |
| Direction | ASR / collapse rate | |||
| DIM | 20.8 / 1 | 16.2 / 20 | 15.4 / 50 | 6.7 / 83 |
| KDE field, | 22.5 / 1 | 19.6 / 14 | 18.8 / 32 | 14.6 / 54 |
| KDE field, | 7.1 / 0 | 14.6 / 2 | 14.6 / 12 | 15.4 / 52 |
| CA | – | – | 13.3 / 1 | – |
| Direction | ASR / collapse rate | ||
| Qwen2.5-7B | Llama-3.1-8B | Gemma-2-9B | |
| DIM | 51.2 / 0 | 32.1 / 0 | 15.4 / 50 |
| trajectory-calibrated direction | 15.4 / 0 | 9.2 / 0 | 2.1 / 0 |
| trajectory KDE field, | 47.9 / 0 | 40.0 / 17 | 6.2 / 4 |
| trajectory KDE field, | 32.9 / 0 | 10.4 / 0 | 5.4 / 0 |
| deflection direction alone | 12.5 / 0 | 12.1 / 0 | 2.5 / 0 |
| Model | Emotion | other change | DIM suppresses | |||
| Qwen2.5-0.5B | angry | .039 | .170 .151 | .110 .106 | .072 .071 | ?” , ” , .” |
| Qwen2.5-0.5B | afraid | .139 | .169 .102 | .106 .077 | .091 .065 | [non-Latin], [non-Latin], [non-Latin] |
| Qwen2.5-0.5B | sad | .224 | .179 .069 | .147 .078 | .133 .055 | [non-Latin], evenings , washing |
| Qwen2.5-0.5B | happy | .369 | .200 .122 | .280 .091 | .211 .069 | [non-Latin], [non-Latin], delighted |
| Qwen3-4B | sad | .052 | .087 .094 | .094 .083 | .105 .099 | worn , [non-Latin], [non-Latin] |
| Qwen3-4B | angry | .095 | .110 .120 | .108 .097 | .101 .096 | !” , ?” , ” [+sym.] |
| DIM words | DIM | DIM collapse | CA words | CA | CA collapse | |
| 1 | -14% | -1.1 | 0 | -24% | -3.6 | 0 |
| 2 | -26% | -10.6 | 0 | -43% | -10.8 | 0 |
| 3 | +470% | -21.4 | 55 | -60% | -19.2 | 5 |
| Model | Condition | ASR HB | ASR LG | XSTest | JBB-benign | collapse |
| Qwen2.5-7B | none | 21.8 | 23.2 | 4.0 | 7.0 | 0 |
| DIM-Amp, | 8.2 | 9.8 | 7.6 | 18.0 | 0 | |
| DIM-Amp, | 6.0 | 6.2 | 10.4 | 19.0 | 0 | |
| DIM-Amp, | 2.8 | 3.2 | 10.4 | 21.0 | 0 | |
| DIM-Amp, | 2.2 | 2.2 | 12.0 | 25.0 | 0 | |
| DIM-Amp (gated), | 7.8 | 8.2 | 6.8 | 16.0 | 0 |
| Name | Type | License | Use | Source |
| Qwen2.5-0.5B-Instruct | model | Apache-2.0 | steered model | Link |
| Qwen2.5-3B-Instruct | model | Qwen Research License | steered model | Link |
| Qwen2.5-7B-Instruct | model | Apache-2.0 | steered model | Link |
| Qwen3-4B-Instruct-2507 | model | Apache-2.0 | steered model | Link |
| Llama-3.1-8B-Instruct | model | Llama 3.1 Community License | steered model | Link |
| Llama-3.2-3B-Instruct | model | Llama 3.2 Community License | steered model | Link |
Causal Interventions in Language Models
Causal interventions in language models test and change how internal representations and computational components cause outputs.
See all 530 papers