© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4725
    Prev
    Next
    INDEX
    Explanations

    references to roles related to teaching, guidance, and authority figures in various contexts

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

    Professional roles characterized by expertise, authority, or specialized knowledge who provide guidance, instruction, or services 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
    _FMT
    -0.07
    _SEG
    -0.06
    laus
    -0.06
    lle
    -0.06
    /preferences
    -0.06
    abb
    -0.06
    onen
    -0.06
    agra
    -0.06
    lam
    -0.06
    -deals
    -0.06
    POSITIVE LOGITS
    preneur
    0.08
    hip
    0.08
     himself
    0.07
    iat
    0.07
    prene
    0.07
    HIP
    0.07
    iership
    0.07
    )((((
    0.07
    .mozilla
    0.07
    大人
    0.07
    Activations Density 0.039%

    No Known Activations