© 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. 126350
    Prev
    Next
    INDEX
    Explanations

    references to categories and classifications in various contexts

    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
     ordinary
    -0.06
    _COMPILE
    -0.06
    'an
    -0.06
    esseract
    -0.06
     franca
    -0.06
    ctp
    -0.06
     baik
    -0.06
    ABCDEFG
    -0.06
    zcze
    -0.06
     Breed
    -0.06
    POSITIVE LOGITS
     category
    0.08
     section
    0.07
    /category
    0.07
    category
    0.07
    misc
    0.07
    /misc
    0.07
     dealing
    0.06
     miscellaneous
    0.06
    section
    0.06
     devoted
    0.06
    Activations Density 0.038%

    No Known Activations