© 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. 22535
    Prev
    Next
    INDEX
    Explanations

    evade detection, analysis, sexting, cost basis

    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
    kontakte
    -0.08
     TLabel
    -0.08
    .metamodel
    -0.08
     Erotische
    -0.08
    çĽijåIJ¬é¡µéĿ¢
    -0.08
     RuntimeObject
    -0.07
    ãĢĤæľ¬
    -0.07
    ีà¹Ģà¸Ķ
    -0.07
    Ä°R
    -0.07
     fChain
    -0.07
    POSITIVE LOGITS
    opi
    0.08
    0.08
     ********************************************************************************
    0.07
    imens
    0.07
    Âł
    0.07
     latter
    0.07
    imen
    0.07
    '
    0.07
    memberof
    0.07
    .CreateIndex
    0.06
    Activations Density 0.331%

    No Known Activations