© 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. 9-LLAMASCOPE-RES-131K
    11. 95495
    Prev
    Next
    INDEX
    Explanations

    words or terms related to physical injury or medical conditions

    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
     Bowman
    -0.08
    ocommerce
    -0.07
    REFIX
    -0.06
     CrossAxisAlignment
    -0.06
    ias
    -0.06
    plib
    -0.06
    asto
    -0.06
    andom
    -0.06
    oen
    -0.06
    елÑĮзÑı
    -0.06
    POSITIVE LOGITS
    ÑĪÑĤов
    0.07
    avras
    0.07
    jad
    0.06
    olean
    0.06
    iola
    0.06
    UNT
    0.06
    atel
    0.06
    dad
    0.06
    ANC
    0.06
    lector
    0.06
    Activations Density 0.000%

    No Known Activations