© 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 EvalsExportsAPI 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. 61085
    Prev
    Next
    INDEX
    Explanations

    references to external links or citations

    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
    æĸĻ
    -0.07
    ebi
    -0.07
    illos
    -0.07
    Terminal
    -0.07
    Ñģм
    -0.06
     çı
    -0.06
     ÑĨÑĸ
    -0.06
    lastic
    -0.06
    velope
    -0.06
    asti
    -0.06
    POSITIVE LOGITS
    (By
    0.07
    _ONCE
    0.06
     Patterson
    0.06
     Patri
    0.06
     Garr
    0.06
    atoria
    0.06
    umed
    0.06
    .gdx
    0.06
    .const
    0.06
    _marshall
    0.06
    Activations Density 0.000%

    No Known Activations