© 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. 28877
    Prev
    Next
    INDEX
    Explanations

    references to side effects and complications related to medical procedures

    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
    osas
    -0.07
    _FF
    -0.07
    iated
    -0.07
    abd
    -0.07
    ikal
    -0.06
    bose
    -0.06
    yor
    -0.06
    istol
    -0.06
    ียà¸Ķ
    -0.06
    ulur
    -0.06
    POSITIVE LOGITS
     temporary
    0.07
     Temporary
    0.07
    788
    0.07
    temporary
    0.07
     transient
    0.06
     disc
    0.06
    TextNode
    0.06
     Blueprint
    0.06
    sworth
    0.06
    iston
    0.06
    Activations Density 0.007%

    No Known Activations