© 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. 10166
    Prev
    Next
    INDEX
    Explanations

    put in, them about, is on, struggled to

    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
    amp
    -0.08
    alse
    -0.08
    /of
    -0.08
     ë¨
    -0.08
    éļĽ
    -0.08
    ucker
    -0.08
     ragaz
    -0.08
    izm
    -0.08
     fore
    -0.07
    aus
    -0.07
    POSITIVE LOGITS
    apult
    0.08
    setattr
    0.08
    ãģĵãģĿ
    0.08
    .mvp
    0.08
     tear
    0.08
    rones
    0.08
    agal
    0.07
     Herman
    0.07
     CascadeType
    0.07
    Îŀ
    0.07
    Activations Density 0.018%

    No Known Activations