© 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. 76246
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and control flow statements

    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
    469
    -0.06
    ior
    -0.06
    ing
    -0.06
    ingen
    -0.06
    elm
    -0.06
    artment
    -0.06
    iva
    -0.06
    oretical
    -0.06
    /or
    -0.06
    con
    -0.06
    POSITIVE LOGITS
    undles
    0.07
    veis
    0.07
    wards
    0.07
    erule
    0.07
    lish
    0.07
    ĶåĽŀ
    0.07
    ières
    0.07
    PFN
    0.07
    ownik
    0.07
    tlement
    0.06
    Activations Density 0.019%

    No Known Activations