© 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. 57113
    Prev
    Next
    INDEX
    Explanations

    SQL statements

    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
    HeaderCode
    -0.14
    OffsetTable
    -0.12
    CallCheck
    -0.12
    GuidId
    -0.12
    GenerationStrategy
    -0.11
    SupportedContent
    -0.11
    oret
    -0.10
    RuntimeObject
    -0.10
    CloseOperation
    -0.10
     )\n\n\n\n\n\n\n\n
    -0.10
    POSITIVE LOGITS
     data
    0.10
    abor
    0.10
    ï¿
    0.10
     foo
    0.09
     TBD
    0.09
     damage
    0.09
    Parms
    0.09
    ---
    0.09
     recap
    0.09
     smo
    0.08
    Activations Density 0.057%

    No Known Activations