© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1094
    Prev
    Next
    INDEX
    Explanations

    titles or roles related to guidance and oversight in various contexts

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

    Professional roles or occupations that provide specialized services, expertise, or guidance to others.

    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
    ίÏīν
    -0.07
    arkin
    -0.07
    ogg
    -0.07
    uding
    -0.06
    ëĿ¼ë§Ī
    -0.06
    zar
    -0.06
     Punch
    -0.06
    Ñİк
    -0.06
    CED
    -0.06
    /windows
    -0.06
    POSITIVE LOGITS
    preneur
    0.08
    (s
    0.08
    ship
    0.07
     who
    0.07
    896
    0.07
    hood
    0.07
    hip
    0.07
    cano
    0.06
    们
    0.06
    isse
    0.06
    Activations Density 0.023%

    No Known Activations