© 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. 57333
    Prev
    Next
    INDEX
    Explanations

    multi-head attention

    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
    elters
    -0.10
     Sou
    -0.10
     sou
    -0.10
     soul
    -0.10
    ok
    -0.09
     nap
    -0.09
     preprocess
    -0.09
     Nap
    -0.09
     Chin
    -0.09
     boot
    -0.09
    POSITIVE LOGITS
     torch
    0.10
     losses
    0.10
    onet
    0.09
     momentum
    0.09
     squeeze
    0.09
    .sg
    0.09
    å¤
    0.09
     squeezing
    0.09
     racially
    0.09
    instanc
    0.09
    Activations Density 0.004%

    No Known Activations