© 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. 128981
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions and symptoms in medical 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
     Bailey
    -0.06
     incumbent
    -0.06
    nam
    -0.06
     Vie
    -0.06
    rend
    -0.06
    aily
    -0.05
    precated
    -0.05
    ÏĢα
    -0.05
    itone
    -0.05
    added
    -0.05
    POSITIVE LOGITS
     thus
    0.10
     therefore
    0.10
     often
    0.09
     usually
    0.08
     sometimes
    0.08
     wiÄĻc
    0.08
     typically
    0.08
     contrast
    0.08
    ALSE
    0.08
     commonly
    0.08
    Activations Density 0.042%

    No Known Activations