© 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. 60871
    Prev
    Next
    INDEX
    Explanations

    details related to medical events and accidents

    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
    resco
    -0.07
     dbl
    -0.07
    APO
    -0.07
    stadt
    -0.07
    acre
    -0.07
    readcr
    -0.07
    onna
    -0.07
     wParam
    -0.06
     Dunn
    -0.06
    otts
    -0.06
    POSITIVE LOGITS
     villagers
    0.06
     p
    0.06
     sharp
    0.06
    urement
    0.06
     cant
    0.05
     bore
    0.05
    uner
    0.05
     locals
    0.05
    itar
    0.05
     .
    0.05
    Activations Density 0.011%

    No Known Activations