© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125876
    Prev
    Next
    INDEX
    Explanations

    references to global rankings or reports related to institutions

    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
    opard
    -0.07
    Orm
    -0.06
    edia
    -0.06
    elters
    -0.06
    ori
    -0.06
     Gran
    -0.06
    PerPixel
    -0.06
    .rdf
    -0.06
    ocument
    -0.06
    paged
    -0.06
    POSITIVE LOGITS
    ’ÑĹ
    0.07
    ovich
    0.07
    298
    0.07
    itary
    0.06
    asser
    0.06
     Wich
    0.06
    inction
    0.06
    iture
    0.06
    _coef
    0.06
    698
    0.06
    Activations Density 0.000%

    No Known Activations