© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 86641
    Prev
    Next
    INDEX
    Explanations

    verbs and activities that indicate expression, solving problems, or monitoring progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dán
    -0.09
    jist
    -0.09
     serg
    -0.09
     kê
    -0.09
     poil
    -0.08
    wchar
    -0.08
    .Serial
    -0.08
    acco
    -0.08
     имÑĥ
    -0.08
    ngth
    -0.08
    POSITIVE LOGITS
    OperationException
    0.06
     shar
    0.06
    Âł
    0.06
    lt
    0.05
    []
    0.05
     Hum
    0.05
     (
    0.05
    idden
    0.05
     pin
    0.05
    odem
    0.05
    Activations Density 0.070%

    No Known Activations