© 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. 3928
    Prev
    Next
    INDEX
    Explanations

    terms related to specific medical therapies and adjustments

    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
    onga
    -0.08
    ëŀ¨
    -0.07
     manic
    -0.06
     Pip
    -0.06
    íĻ©
    -0.06
     ÙħØ´
    -0.06
    iants
    -0.06
    /tos
    -0.06
    pill
    -0.06
     flank
    -0.06
    POSITIVE LOGITS
     fasc
    0.07
    istem
    0.07
     micro
    0.06
    assage
    0.06
     sadd
    0.06
    ocy
    0.06
    ect
    0.06
     Ellen
    0.06
    agma
    0.06
    esin
    0.06
    Activations Density 0.001%

    No Known Activations