© 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. 60670
    Prev
    Next
    INDEX
    Explanations

    references to art, education, and organization in an institutional context

    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
    Grade
    -0.08
     Grade
    -0.07
     grade
    -0.07
    GRADE
    -0.06
    grades
    -0.06
    grade
    -0.06
    à¥Ģà¤ķरण
    -0.06
    вол
    -0.06
    actionDate
    -0.05
    reek
    -0.05
    POSITIVE LOGITS
    obot
    0.08
    /proto
    0.08
    ernaut
    0.07
     Bau
    0.07
    school
    0.07
    mitters
    0.07
    raki
    0.06
    utm
    0.06
    ilters
    0.06
     experiment
    0.06
    Activations Density 0.001%

    No Known Activations