© 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. 61232
    Prev
    Next
    INDEX
    Explanations

    programming-related header definitions and their associated values or conditions

    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
     пал
    -0.07
    oÅĻ
    -0.06
    iguous
    -0.06
    541
    -0.06
    INGS
    -0.06
    IPLE
    -0.06
    夢
    -0.06
     pled
    -0.06
    ýš
    -0.06
    æģµ
    -0.06
    POSITIVE LOGITS
     Cache
    0.09
     cache
    0.09
    .Cache
    0.09
    ocache
    0.09
    Expires
    0.08
    -cache
    0.08
    Cache
    0.08
    (cache
    0.08
    /cache
    0.07
    .cache
    0.07
    Activations Density 0.001%

    No Known Activations