© 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. 806
    Prev
    Next
    INDEX
    Explanations

    programming terminology and structures related to data and algorithms

    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
    Ìģc
    -0.07
    krom
    -0.07
    æĺĮ
    -0.07
    udeau
    -0.07
     \`
    -0.06
    Ñĥмов
    -0.06
    æļĸ
    -0.06
    ATAR
    -0.06
    ÐIJÐł
    -0.06
    adge
    -0.06
    POSITIVE LOGITS
    imat
    0.06
    Decorator
    0.06
     Weiner
    0.06
     unwind
    0.06
     ***!↵
    0.06
    993
    0.06
     basket
    0.06
     kariy
    0.06
    ãĥ¼ãĥĵ
    0.06
    (formatter
    0.06
    Activations Density 0.034%

    No Known Activations