© 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. 126876
    Prev
    Next
    INDEX
    Explanations

    terms related to buying and online transactions, particularly in the context of pharmaceuticals and gaming

    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
    /*č↵
    -0.07
    (æĹ¥
    -0.07
     Lexer
    -0.07
    GGLE
    -0.07
    ãĢ
    -0.07
    ozor
    -0.07
    reds
    -0.06
    Ïħκ
    -0.06
     оглÑı
    -0.06
    ãĤ
    -0.06
    POSITIVE LOGITS
    (fabs
    0.06
    atz
    0.06
    _formats
    0.06
    asha
    0.06
    ÂĢÂ
    0.05
    bjerg
    0.05
    Õ¡
    0.05
    ospace
    0.05
     jsonResponse
    0.05
    ¤ëĭ¤
    0.05
    Activations Density 0.003%

    No Known Activations