© 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. 118523
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recommended reading or listening for specific audiences

    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
    bla
    -0.07
     spontaneous
    -0.06
    .ncbi
    -0.06
    곤
    -0.06
    ark
    -0.06
    aterno
    -0.06
    elry
    -0.06
    OrFail
    -0.06
     FactoryBot
    -0.06
    bserv
    -0.06
    POSITIVE LOGITS
     anyone
    0.07
     unread
    0.07
    //**↵
    0.07
     Anyone
    0.07
    ingleton
    0.07
    _HANDLE
    0.07
     reads
    0.07
    /read
    0.07
     Understanding
    0.06
    _read
    0.06
    Activations Density 0.021%

    No Known Activations