© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1479
    Prev
    Next
    INDEX
    Explanations

    topics, object, parameter, service, program, front, nation, answer, query, products, plan

    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
    EMPLARY
    -0.10
    .Formatter
    -0.10
     FetchType
    -0.09
    Ø
    -0.09
    RITE
    -0.09
    BuilderFactory
    -0.09
    ÐŁÐļ
    -0.09
    Âģ@
    -0.09
    įng
    -0.08
    FormattedMessage
    -0.08
    POSITIVE LOGITS
    am
    0.10
    ot
    0.09
    pl
    0.09
    ia
    0.09
    ym
    0.09
    zz
    0.09
    ains
    0.09
     Lew
    0.09
    ag
    0.09
     Zub
    0.09
    Activations Density 0.409%

    No Known Activations