© 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. 84104
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or experiences

    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
    ãģ°ãģĭãĤĬ
    -0.09
    wap
    -0.08
    upo
    -0.07
    ãģ»ãģ©
    -0.07
    achs
    -0.07
    .datab
    -0.07
    ffi
    -0.07
    /TT
    -0.07
    å¹¹ç·ļ
    -0.07
    611
    -0.07
    POSITIVE LOGITS
     among
    0.07
     Among
    0.07
     amongst
    0.07
    olit
    0.07
     whom
    0.06
    inea
    0.06
     certainly
    0.06
    isure
    0.06
     cin
    0.06
     whose
    0.06
    Activations Density 0.001%

    No Known Activations