© 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. 17-LLAMASCOPE-RES-131K
    6. 106104
    Prev
    Next
    INDEX
    Explanations

    organizational structures and collaborations involving committees and teams

    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
    TECTED
    -0.08
     addCriterion
    -0.08
    TOTYPE
    -0.08
    ÑĦоÑĢми
    -0.07
    AGR
    -0.07
    _IRQHandler
    -0.07
    tember
    -0.07
    vá
    -0.07
    rello
    -0.06
    .li
    -0.06
    POSITIVE LOGITS
     staff
    0.23
     team
    0.21
    staff
    0.17
     Staff
    0.17
     crew
    0.16
    Staff
    0.16
    team
    0.15
    -team
    0.15
     Team
    0.14
     teams
    0.13
    Activations Density 0.085%

    No Known Activations