© 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. 9676
    Prev
    Next
    INDEX
    Explanations

    city, state separator

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that are part of proper nouns, titles, or formal designations (like place names, company names, and story beginnings).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     damer
    -0.08
    úsqueda
    -0.08
     $($
    -0.08
    irket
    -0.08
     lesbische
    -0.07
     salopes
    -0.07
     ragaz
    -0.07
     ><?
    -0.07
     geschichten
    -0.07
    Lorem
    -0.07
    POSITIVE LOGITS
    .RELATED
    0.08
    .UnitTesting
    0.07
     reuseIdentifier
    0.07
    .moveToNext
    0.07
     addObserver
    0.07
     baģlantılar
    0.07
    illis
    0.07
    stringValue
    0.07
    ãģ¾ãģĽ
    0.06
    0.06
    Activations Density 3.775%

    No Known Activations