© 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. 43424
    Prev
    Next
    INDEX
    Explanations

    negative prefixes (in-, im-, ir-)

    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
    _PUSHDATA
    -0.10
    wiki
    -0.10
    RuleContext
    -0.10
    ampo
    -0.10
     DERP
    -0.09
    beros
    -0.09
    oyo
    -0.09
    atively
    -0.09
    EMPLARY
    -0.09
    ActionCode
    -0.09
    POSITIVE LOGITS
    /il
    0.17
    /problem
    0.14
    ly
    0.13
    ities
    0.12
    /out
    0.12
    iciencies
    0.11
    cies
    0.11
    /question
    0.11
    ancies
    0.11
    itude
    0.10
    Activations Density 0.089%

    No Known Activations