© 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. 87230
    Prev
    Next
    INDEX
    Explanations

    references to government policies or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Paragraph or section breaks that separate distinct units of content, often appearing immediately before a new paragraph, numbered item, or topic begins.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Rig
    -0.07
    er
    -0.07
    ãĥ£
    -0.07
    ouce
    -0.07
    oller
    -0.07
    olver
    -0.07
    entre
    -0.07
    ORT
    -0.06
     addCriterion
    -0.06
    assa
    -0.06
    POSITIVE LOGITS
    .wikipedia
    0.07
    boBox
    0.07
    Ø¡
    0.06
     ÑģилÑĥ
    0.06
    orf
    0.06
    orama
    0.06
    uno
    0.06
    lico
    0.06
    kaç
    0.06
    447
    0.06
    Activations Density 0.256%

    No Known Activations