© 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. 15-LLAMASCOPE-RES-131K
    11. 816
    Prev
    Next
    INDEX
    Explanations

    references to measurements and calculations related to technology

    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
    گاÙĨÛĮ
    -0.08
    .vn
    -0.07
    ichte
    -0.06
    lobs
    -0.06
    gis
    -0.06
     perv
    -0.06
     Ant
    -0.06
    ãģŁãģı
    -0.06
    GST
    -0.06
    emes
    -0.06
    POSITIVE LOGITS
    rome
    0.07
    arma
    0.07
    ses
    0.07
    ÑĮе
    0.06
    rens
    0.06
     Scho
    0.06
     Majority
    0.06
    uit
    0.06
    ÂĢÂ
    0.06
    ium
    0.06
    Activations Density 0.051%

    No Known Activations