© 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. 76707
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and link elements in a document's head section

    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
    itz
    -0.07
    orman
    -0.07
    rex
    -0.06
    bane
    -0.06
     treff
    -0.06
    arkin
    -0.06
    /fixtures
    -0.06
    cház
    -0.06
     commod
    -0.06
    sein
    -0.06
    POSITIVE LOGITS
    WISE
    0.07
    ourcem
    0.07
    icas
    0.06
    oleÄį
    0.06
    canf
    0.06
    Ñĩив
    0.06
    atk
    0.06
    .react
    0.06
    quia
    0.06
    ãĥĶãĥ¼
    0.06
    Activations Density 0.001%

    No Known Activations