© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127149
    Prev
    Next
    INDEX
    Explanations

    references to injuries and 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
     crem
    -0.07
    Leap
    -0.06
    ansen
    -0.06
    edral
    -0.06
    ÑĨе
    -0.06
    ลà¸ĩ
    -0.06
     ra
    -0.06
    ILITY
    -0.06
     house
    -0.06
    izzle
    -0.06
    POSITIVE LOGITS
     concussion
    0.14
     Conc
    0.11
    conc
    0.11
     conc
    0.09
     brain
    0.08
     Brain
    0.08
    brain
    0.08
    Head
    0.07
    /head
    0.07
    Ãłng
    0.07
    Activations Density 0.005%

    No Known Activations