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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 105874
    Prev
    Next
    INDEX
    Explanations

    roles related to guidance and support within organizations or educational contexts

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

    Tokens referring to professional service providers who assist, advise or support clients/customers. These include consultants, experts, representatives, advisors, instructors, staff members, directors, and team members who offer specialized knowledge or assistance.

    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
     Ñĥж
    -0.07
     αÏħÏĦÏĮ
    -0.07
    agas
    -0.07
    ouz
    -0.07
    ipar
    -0.07
     Directed
    -0.07
    ³
    -0.07
    ढ
    -0.06
    ensi
    -0.06
    /Typography
    -0.06
    POSITIVE LOGITS
     who
    0.08
    bite
    0.06
     Bite
    0.06
     bite
    0.06
     wet
    0.06
    anger
    0.06
    ležit
    0.06
    spath
    0.06
    706
    0.06
    who
    0.06
    Activations Density 0.016%

    No Known Activations