© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    terms related to treatment efficacy 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
     sebe
    -0.07
     बल
    -0.07
    OTO
    -0.07
    Boom
    -0.06
    .scalablytyped
    -0.06
    ohn
    -0.06
    IGO
    -0.06
    _BGR
    -0.06
    izo
    -0.06
    ī´
    -0.06
    POSITIVE LOGITS
     achieved
    0.10
     improvement
    0.07
     achievement
    0.07
     achieves
    0.07
     achieving
    0.07
    issant
    0.07
     Improvement
    0.07
     Achie
    0.07
     outcome
    0.07
     achieve
    0.06
    Activations Density 0.022%

    No Known Activations