© 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. 94102
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to figures or tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation and transition markers that structure explanatory content in technical or academic writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    utherland
    -0.07
    mmo
    -0.07
    lesen
    -0.07
    edin
    -0.06
    меÑĩ
    -0.06
    تب
    -0.06
    eydi
    -0.06
    _MM
    -0.06
     гоÑģподаÑĢ
    -0.06
     hete
    -0.06
    POSITIVE LOGITS
     latter
    0.08
     meaning
    0.07
     definition
    0.07
     Meaning
    0.07
    meaning
    0.07
     Definitions
    0.06
     Definition
    0.06
    isko
    0.06
    Definitions
    0.06
    æĦıæĢĿ
    0.06
    Activations Density 0.099%

    No Known Activations