© 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. 78231
    Prev
    Next
    INDEX
    Explanations

    components related to significant decisions or rulings

    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
    .Localization
    -0.07
     ãĤ¢ãĤ¤
    -0.07
    ÑĩÑĥк
    -0.07
    åĸĦ
    -0.07
    ocker
    -0.07
    incinn
    -0.07
    à¥ĩण
    -0.07
    ocab
    -0.07
    /Library
    -0.06
    _capabilities
    -0.06
    POSITIVE LOGITS
    oub
    0.09
    201
    0.07
    orex
    0.07
    200
    0.07
    ends
    0.06
    iline
    0.06
     Townsend
    0.06
    ews
    0.06
    uros
    0.06
    own
    0.06
    Activations Density 0.008%

    No Known Activations