Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106281
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and diagnoses

    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
    .matcher
    -0.06
    оÑĢалÑĮ
    -0.06
    -san
    -0.06
    æŀ
    -0.06
    unities
    -0.06
    foil
    -0.06
    _MISSING
    -0.06
     skeletons
    -0.06
    /gin
    -0.06
    .exec
    -0.06
    POSITIVE LOGITS
     harmless
    0.08
     size
    0.07
     growth
    0.07
     benign
    0.07
     removal
    0.07
    UBY
    0.07
     Surveillance
    0.07
     Size
    0.07
     sizes
    0.07
     surveillance
    0.07
    Activations Density 0.006%

    No Known Activations