© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 94662
    Prev
    Next
    INDEX
    Explanations

    references to the user or audiences being addressed

    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
    isse
    -0.07
     Hopkins
    -0.06
     forthcoming
    -0.06
    967
    -0.06
    ils
    -0.06
    adoo
    -0.06
     Dennis
    -0.06
     chi
    -0.06
    oly
    -0.06
    好çļĦ
    -0.05
    POSITIVE LOGITS
    UCKET
    0.07
    &a
    0.07
    cdb
    0.07
    ARIO
    0.07
    adero
    0.07
    YRO
    0.07
    ÑĢап
    0.07
    äre
    0.07
    QueryParam
    0.07
    à¤¾à¤Ł
    0.07
    Activations Density 0.000%

    No Known Activations