© 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. 17500
    Prev
    Next
    INDEX
    Explanations

    reinforcement learning or keywords

    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
     Gur
    -0.09
     lad
    -0.08
    peak
    -0.08
    nbsp
    -0.08
    .ImageAlign
    -0.08
    jid
    -0.08
    /dd
    -0.08
    088
    -0.08
    solete
    -0.08
    585
    -0.08
    POSITIVE LOGITS
    (sp
    0.11
     [_
    0.11
    AtA
    0.09
    ERSIST
    0.08
     ​​
    0.08
    rella
    0.08
    GuidId
    0.08
    ARSER
    0.08
    weigh
    0.08
    (stdin
    0.08
    Activations Density 0.366%

    No Known Activations