© 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. 126053
    Prev
    Next
    INDEX
    Explanations

    HTML comment tags and related markup elements

    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
    ắp
    -0.08
    ych
    -0.07
    grave
    -0.07
     fitte
    -0.07
    ILA
    -0.07
    ekk
    -0.07
    vyk
    -0.07
    ToLeft
    -0.07
    Æ°á»Ł
    -0.07
    respuesta
    -0.07
    POSITIVE LOGITS
    i
    0.08
    ftware
    0.07
    a
    0.07
    structions
    0.06
    istical
    0.06
    A
    0.06
    957
    0.06
    ży
    0.06
    uliar
    0.06
    B
    0.06
    Activations Density 0.003%

    No Known Activations