© 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. 119093
    Prev
    Next
    INDEX
    Explanations

    terms related to healing or treatments for 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
    ized
    -0.08
    shire
    -0.08
    lig
    -0.08
    Ú¯ÛĮر
    -0.08
    kaar
    -0.07
    ize
    -0.07
    lor
    -0.07
    redo
    -0.07
    rome
    -0.07
    IZED
    -0.07
    POSITIVE LOGITS
    ative
    0.07
    ios
    0.06
    unami
    0.06
     Byl
    0.06
    grass
    0.06
    idth
    0.06
    ious
    0.06
    -all
    0.06
    illance
    0.06
    /add
    0.06
    Activations Density 0.003%

    No Known Activations