© 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. 118486
    Prev
    Next
    INDEX
    Explanations

    terms related to voting and voters

    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
    horn
    -0.06
     Lup
    -0.06
    olet
    -0.06
     åįİ
    -0.06
    .timeScale
    -0.06
    èı¯
    -0.06
    bold
    -0.06
    uyu
    -0.06
    ANCH
    -0.06
    incinn
    -0.06
    POSITIVE LOGITS
    atee
    0.07
    fal
    0.06
     aras
    0.06
    ιÏİ
    0.06
     полоÑĤ
    0.06
    ORIZATION
    0.06
    atch
    0.06
    activex
    0.06
    ´Ģ
    0.06
    .scalablytyped
    0.06
    Activations Density 0.000%

    No Known Activations