© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38326
    Prev
    Next
    INDEX
    Explanations

    oppression, harassment, torture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    /current
    -0.10
    733
    -0.09
    bie
    -0.09
    assy
    -0.09
    432
    -0.09
    ROID
    -0.08
     ​​
    -0.08
     Herb
    -0.08
    bread
    -0.08
     bread
    -0.08
    POSITIVE LOGITS
     tactics
    0.13
    /dom
    0.12
    /mock
    0.11
     Tactics
    0.11
    ниÑĩеÑģ
    0.10
     Fang
    0.10
     Annunci
    0.10
    /op
    0.10
    /bash
    0.10
    geist
    0.09
    Activations Density 0.099%

    No Known Activations