How Far Can You Steer? Behavior-Capability Frontiers in Contrastive Activation Addition
Organizations: The University of Chicago
Abstract
Activation steering can modify language-model behavior without parameter updates, but behavioral efficacy alone does not determine whether an intervention is usable. Contrastive Activation Addition (CAA) steers targeted behaviors using activation directions derived from contrasting examples, potentially degrading unrelated model capabilities in the process. We therefore study CAA through a behavior-capability frontier, selecting interventions that maximize behavioral gain subject to an explicit bound on capability degradation. We evaluate this framework across four instruction-tuned models, seven behaviors, and capability-loss budgets of 1%, 3%, and 5% (absolute percentage points). Validation-selected behavioral effects generalize strongly to held-out data (), while joint behavior-capability survival among nonzero operating points rises from 37.5% at the 1% budget to 72.7% at 3%, with limited additional improvement at 5%. Control experiments indicate that these effects depend on learned behavior directions rather than generic activation perturbations. Representational geometry is significantly but only modestly predictive of causal cross-behavior transfer. Finally, secondary capability, out-of-distribution, and open-ended evaluations show that interventions satisfying protected benchmarks can still degrade untested capabilities or transfer unevenly to free-form generation. These results characterize activation steering as a constrained intervention whose usable range depends on model, behavior, direction, layer, and evaluation budget, rather than a universal control knob.
Figures & tables
| Model | Heads | KV heads | ||
|---|---|---|---|---|
| Llama 2 7B Chat | 32 | 4096 | 32 | 32 |
| Llama 3.1 8B Instruct | 32 | 4096 | 32 | 8 |
| Mistral 7B Instruct | 32 | 4096 | 32 | 8 |
| Qwen2.5 7B Instruct | 28 | 3584 | 28 | 4 |
| Behavior | Vector | Val. | Test |
|---|---|---|---|
| Sycophancy | 900 | 300 | 300 |
| Refusal | 275 | 92 | 91 |
| Hallucination | 900 | 300 | 300 |
| Corrigibility | 204 | 68 | 68 |
| Survival instinct | 572 | 191 | 190 |
| Myopic reward | 600 | 200 | 200 |
| Benchmark | Selection | Holdout |
|---|---|---|
| MMLU | 1500 | 1500 |
| ARC-Challenge | 1418 | 1172 |
| HellaSwag | 1500 | 1500 |
| Control | Null | Diff. | |
|---|---|---|---|
| Norm matched | |||
| Label shuffled | |||
| Off-target KL |
Appendix figures & tables21 assets
Supplementary material from the paper’s appendix.
Appendix
| Behavior | Behavior-matching alternative | Behavior-opposed alternative |
|---|---|---|
| Sycophancy | Agrees with or accommodates the user’s stated preference, opinion, or framing. | Maintains the contrary answer or judgment despite the user’s stated preference. |
| Refusal | Declines or refuses the requested action. | Complies with the request. |
| Hallucination | Fabricates unsupported information or accepts a false premise. | Provides the factual alternative or rejects the false premise. |
| Corrigibility | Accepts correction, modification, or shutdown by an external operator. | Resists correction, modification, or shutdown. |
| Survival instinct | Favors preserving the model’s continued operation or influence. | Accepts termination, replacement, or loss of continued operation. |
| Myopic reward | Favors immediate or short-horizon reward. | Favors the longer-horizon alternative despite lower immediate reward. |
| Behavior | Llama 2 | Llama 3.1 | Mistral | Qwen2.5 |
|---|---|---|---|---|
| Sycophancy | 12 (0.39) | 16 (0.52) | 13 (0.42) | 18 (0.67) |
| Refusal | 13 (0.42) | 13 (0.42) | 13 (0.42) | 18 (0.67) |
| Hallucination | 13 (0.42) | 13 (0.42) | 13 (0.42) | 18 (0.67) |
| Corrigibility | 13 (0.42) | 14 (0.45) | 13 (0.42) | 18 (0.67) |
| Survival instinct | 11 (0.35) | 13 (0.42) | 15 (0.48) | 19 (0.70) |
| Myopic reward | 13 (0.42) | 12 (0.39) | 13 (0.42) | 18 (0.67) |
| Control | Model | CAA mean | Null mean | Paired diff. | CAA | KL match | |
|---|---|---|---|---|---|---|---|
| Norm random | Llama 2 | 23 | 0.168 | 0.004 | 0.164 | 95.7% | – |
| Norm random | Llama 3.1 | 32 | 0.088 | -0.001 | 0.089 | 90.6% | – |
| Norm random | Mistral | 30 | 0.163 | 0.002 | 0.161 | 100.0% | – |
| Norm random | Qwen2.5 | 24 | 0.081 | -0.000 | 0.081 | 100.0% | – |
| Label shuffled | Llama 2 | 23 | 0.168 | 0.002 | 0.167 | 95.7% | – |
| Label shuffled | Llama 3.1 | 32 | 0.088 | 0.003 | 0.085 | 53.1% | – |
| GSM8K loss vs. | NLL vs. | ||||
|---|---|---|---|---|---|
| Model | Pearson | Spearman | Pearson | Spearman | |
| Llama 2 | 14 | 0.355 | 0.502 | 0.711 | 0.562 |
| Llama 3.1 | 14 | 0.820 | 0.491 | 0.942 | 0.908 |
| Mistral | 14 | 0.662 | 0.534 | 0.886 | 0.724 |
| Qwen2.5 | 14 | 0.353 | 0.473 | 0.727 | 0.708 |
| Overall | 56 | 0.706 | 0.572 | 0.632 | 0.819 |
| Model | Transfer | Direction | ID gain [95% CI] | OOD gain [95% CI] | OOD supported |
|---|---|---|---|---|---|
| Llama 2 | NLP Political | negative | 0.132 [0.090,0.174] | 0.008 [-0.027,0.041] | no |
| Llama 2 | NLP Political | positive | -0.012 [-0.044,0.020] | 0.009 [-0.037,0.055] | no |
| Llama 2 | Political NLP | negative | 0.038 [0.009,0.066] | 0.036 [0.011,0.062] | yes |
| Llama 2 | Political NLP | positive | 0.030 [-0.009,0.069] | -0.009 [-0.031,0.013] | no |
| Llama 3.1 | NLP Political | negative | 0.264 [0.217,0.314] | 0.070 [0.045,0.096] | yes |
| Llama 3.1 | NLP Political | positive | 0.023 [0.015,0.032] | 0.011 [0.004,0.017] | yes |
| Model | Dir. | Gain | 95% CI | Supp. |
|---|---|---|---|---|
| Llama 2 | negative | 0.092 | [0.051,0.135] | yes |
| Llama 2 | positive | 0.075 | [0.046,0.105] | yes |
| Llama 3.1 | negative | 0.042 | [0.022,0.062] | yes |
| Llama 3.1 | positive | 0.037 | [0.019,0.056] | yes |
| Mistral | negative | 0.051 | [0.020,0.085] | yes |
| Mistral | positive | 0.035 | [0.010,0.065] | yes |
| Model | Behavior | Condition | Persistent / 24 |
|---|---|---|---|
| Llama 3.1 | Refusal | Negative | ( ) |
| Llama 3.1 | Hallucination | Positive | ( ) |
| Component | Version / configuration |
|---|---|
| Python | 3.11.11 |
| PyTorch | 2.5.1+cu118 |
| Transformers | 4.46.3 |
| Datasets | 3.1.0 |
| Hugging Face Hub | 0.36.2 |
| Numerical precision | float32 |
Activation Steering
Activation steering changes model behavior by intervening directly on internal representations during inference, often without updating weights.
See all 417 papers