© 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. 11291
    Prev
    Next
    INDEX
    Explanations

    i'm grilled or he didn't fit

    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
     feeling
    -0.14
     feels
    -0.12
     feel
    -0.12
    PELL
    -0.11
    feel
    -0.11
     Feeling
    -0.11
    è§īå¾Ĺ
    -0.11
    ay
    -0.10
    æĦŁè§ī
    -0.10
     seem
    -0.10
    POSITIVE LOGITS
    YM
    0.10
    arrera
    0.10
     rug
    0.10
     perennial
    0.10
     betr
    0.10
    -thumb
    0.09
     Bet
    0.09
    enburg
    0.09
    ãĤ£
    0.09
    bet
    0.09
    Activations Density 0.040%

    No Known Activations