© 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. 36676
    Prev
    Next
    INDEX
    Explanations

    the name

    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
     abbrev
    -0.10
     numbered
    -0.10
     unidentified
    -0.10
    adiens
    -0.10
     entityType
    -0.10
     keyValue
    -0.09
    Nach
    -0.09
     Nach
    -0.09
    _filepath
    -0.09
     Abb
    -0.09
    POSITIVE LOGITS
     name
    1.03
    name
    0.73
     Name
    0.68
     names
    0.64
    åIJį称
    0.62
    .name
    0.62
    _name
    0.61
    -name
    0.61
    åIJįåŃĹ
    0.60
    Name
    0.58
    Activations Density 0.640%

    No Known Activations