© 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. 53324
    Prev
    Next
    INDEX
    Explanations

    which is, staying within, right child

    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
     discreet
    -0.10
    anou
    -0.10
    aversable
    -0.09
     autogenerated
    -0.09
     ï¼ľ
    -0.09
     accommodation
    -0.08
     resultant
    -0.08
    ERRU
    -0.08
    velle
    -0.08
     {?}
    -0.08
    POSITIVE LOGITS
     *
    0.10
    [*
    0.10
    331
    0.09
     Alice
    0.09
     ``
    0.09
    alen
    0.09
    alog
    0.09
     innoc
    0.09
    iske
    0.09
     legalization
    0.09
    Activations Density 0.026%

    No Known Activations