Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44142
    Prev
    Next
    INDEX
    Explanations

    functions that return string representations

    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
    â̦)
    -0.08
    â̦↵↵
    -0.07
     â̦↵↵
    -0.07
    ...)↵↵
    -0.07
    â̦..
    -0.07
     ...)
    -0.07
    â̦)↵↵
    -0.06
    ...)
    -0.06
    ..."↵↵
    -0.06
     |↵↵
    -0.06
    POSITIVE LOGITS
    |null
    0.14
    |string
    0.12
    ↵
    0.12
    |\
    0.12
    |int
    0.11
    |array
    0.11
    []↵
    0.11
    ;↵
    0.10
     The
    0.09
     mixed
    0.09
    Activations Density 0.018%

    No Known Activations