© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 27649
    Prev
    Next
    INDEX
    Explanations

    primary key identifier

    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
    надлеж
    -0.11
     INDIRECT
    -0.11
    TemplateName
    -0.10
     Keystone
    -0.10
    ObjectName
    -0.09
    _Lean
    -0.09
    .SubItems
    -0.09
    /goto
    -0.09
    TestCategory
    -0.09
    styleType
    -0.09
    POSITIVE LOGITS
     id
    0.32
    id
    0.27
    .id
    0.23
    _id
    0.22
     Id
    0.22
    \tid
    0.21
    (id
    0.21
     ID
    0.20
    Id
    0.20
    ID
    0.18
    Activations Density 0.088%

    No Known Activations