© 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. 15-LLAMASCOPE-RES-131K
    11. 90359
    Prev
    Next
    INDEX
    Explanations

    references to governmental or organizational structures and committees

    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
    iyan
    -0.08
    imb
    -0.07
    ä¿Ĭ
    -0.07
    istrovstvÃŃ
    -0.07
    ampp
    -0.07
    /xhtml
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    pta
    -0.07
    kola
    -0.07
    _EMIT
    -0.07
    POSITIVE LOGITS
     of
    0.09
    466
    0.07
    057
    0.06
     newly
    0.06
     at
    0.06
     Weinstein
    0.06
     responsible
    0.06
     của
    0.06
    led
    0.06
     section
    0.06
    Activations Density 0.018%

    No Known Activations