© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14644
    Prev
    Next
    INDEX
    Explanations

    strategy meets fire

    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
    .gdx
    -0.10
     Grat
    -0.09
     Mori
    -0.09
     outs
    -0.09
    oby
    -0.09
    -caret
    -0.09
    umps
    -0.09
    mlink
    -0.08
     ob
    -0.08
    oller
    -0.08
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.10
     Sofia
    0.09
    anche
    0.09
    Ùij
    0.09
     mend
    0.09
    istic
    0.09
    ulis
    0.09
    yer
    0.09
     drip
    0.09
    -a
    0.09
    Activations Density 0.029%

    No Known Activations