© 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. 33142
    Prev
    Next
    INDEX
    Explanations

    Foreign Key or Primary Key identifiers

    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
    .updateDynamic
    -0.13
     ownerId
    -0.10
     addCriterion
    -0.10
    CallCheck
    -0.10
    UrlParser
    -0.10
    <|begin_of_text|>
    -0.10
    createUrl
    -0.09
    WidthSpace
    -0.09
    FileVersion
    -0.09
    DCALL
    -0.09
    POSITIVE LOGITS
     type
    0.10
     Status
    0.09
    FORE
    0.09
     tipo
    0.09
     setType
    0.09
     status
    0.09
    Readable
    0.09
     reason
    0.09
    apon
    0.09
     amounts
    0.09
    Activations Density 0.196%

    No Known Activations