© 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. 31123
    Prev
    Next
    INDEX
    Explanations

    elements related to musical expression and emotional depth

    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
    çŀ
    -0.06
    bull
    -0.06
     lifelong
    -0.06
     Zug
    -0.06
     Wesley
    -0.05
    ?f
    -0.05
     trump
    -0.05
    650
    -0.05
     Kart
    -0.05
    /address
    -0.05
    POSITIVE LOGITS
    -modal
    0.07
     listeners
    0.07
    vÄĽt
    0.07
    iyan
    0.07
    uspended
    0.06
    iability
    0.06
    ofi
    0.06
    elop
    0.06
    .AutoSizeMode
    0.06
     èĪ
    0.06
    Activations Density 0.021%

    No Known Activations