© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29064
    Prev
    Next
    INDEX
    Explanations

    client name

    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
    Not in Any Lists

    No Comments

    Negative Logits
    errat
    -0.08
    ãĥ¾
    -0.08
    ibri
    -0.08
    ÐĬ
    -0.08
    [at
    -0.08
    reck
    -0.07
    umbn
    -0.07
    /inet
    -0.07
    igidBody
    -0.07
     inappropriate
    -0.07
    POSITIVE LOGITS
    '\n
    0.08
    ']!='
    0.08
    ocard
    0.08
     Scor
    0.08
     FIXME
    0.07
    iza
    0.07
     [âĢ¦]...\n
    0.07
     Pou
    0.07
     exped
    0.07
     Fitzgerald
    0.07
    Activations Density 0.144%

    No Known Activations