© 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. 77045
    Prev
    Next
    INDEX
    Explanations

    references to programming or web development-related terminology

    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
    ruba
    -0.07
    ContentLoaded
    -0.06
    /MPL
    -0.06
     closure
    -0.06
    /google
    -0.06
    ุล
    -0.06
    WEBPACK
    -0.06
     Ø¢ÙĤ
    -0.06
    <source
    -0.06
    /Foundation
    -0.06
    POSITIVE LOGITS
    uo
    0.06
    akh
    0.06
    iswa
    0.06
    izador
    0.06
    .springboot
    0.06
     Osc
    0.06
    anzi
    0.06
    вин
    0.06
    &R
    0.06
    ucc
    0.06
    Activations Density 0.039%

    No Known Activations