© 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. 119137
    Prev
    Next
    INDEX
    Explanations

    biochemical interactions and related scientific 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
    ngrx
    -0.08
    ãģ¨ãģĨ
    -0.07
    lags
    -0.07
    à¸ģรรม
    -0.07
    ombine
    -0.07
    _rq
    -0.07
    odzi
    -0.07
     nest
    -0.07
    ragments
    -0.07
     bow
    -0.07
    POSITIVE LOGITS
     yeast
    0.12
     Portland
    0.09
    Portland
    0.09
     Ye
    0.09
     fungal
    0.08
     Candid
    0.08
     ye
    0.07
     Chile
    0.07
     Rochester
    0.07
     Oregon
    0.07
    Activations Density 0.113%

    No Known Activations