© 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. 62429
    Prev
    Next
    INDEX
    Explanations

    fragments related to notable events or significant statements about teams, players, or organizations

    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
    stem
    -0.08
    ilon
    -0.07
    arel
    -0.07
    inctions
    -0.07
    opsy
    -0.07
    istrate
    -0.07
    engkap
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    PosY
    -0.07
    orio
    -0.07
    POSITIVE LOGITS
     Lap
    0.07
     Gross
    0.07
     Rich
    0.06
     Eff
    0.06
    ATTER
    0.06
     Ha
    0.05
     Glob
    0.05
     Äįist
    0.05
     Jas
    0.05
    WS
    0.05
    Activations Density 0.003%

    No Known Activations