© 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. 5326
    Prev
    Next
    INDEX
    Explanations

    suggestive content or responses

    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
     crap
    -0.10
    .scalablytyped
    -0.10
     fools
    -0.10
     Heck
    -0.10
     Cra
    -0.09
     excell
    -0.09
     Rena
    -0.09
    ANNOT
    -0.09
     nues
    -0.09
    ior
    -0.09
    POSITIVE LOGITS
     god
    0.11
     tits
    0.11
     ì¢
    0.10
     ass
    0.10
     cum
    0.10
     tit
    0.09
     ë¸
    0.09
    ê¸Ķ
    0.09
    ingen
    0.09
     dip
    0.09
    Activations Density 0.010%

    No Known Activations