© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93717
    Prev
    Next
    INDEX
    Explanations

    code snippets or sections of programming languages

    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
    folio
    -0.07
     Rex
    -0.07
     stripslashes
    -0.06
    hire
    -0.06
    /*č↵
    -0.06
    avel
    -0.06
    fol
    -0.06
    oreal
    -0.06
    ียà¸ĩ
    -0.06
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.06
    POSITIVE LOGITS
     zug
    0.06
    oki
    0.06
    agar
    0.06
    ecute
    0.06
    sigmoid
    0.06
    ServletContext
    0.06
    loub
    0.05
    SDL
    0.05
     Hale
    0.05
    ska
    0.05
    Activations Density 0.009%

    No Known Activations