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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96057
    Prev
    Next
    INDEX
    Explanations

    terms and references related to medical conditions and diseases

    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
     jurisdictions
    -0.06
    uki
    -0.06
    ocker
    -0.06
    anki
    -0.06
    ajan
    -0.06
     Phy
    -0.06
    yle
    -0.06
    elm
    -0.05
     lại
    -0.05
    Carthy
    -0.05
    POSITIVE LOGITS
     Russo
    0.06
    æŃ¡
    0.06
    _AF
    0.06
    -msg
    0.06
    .omg
    0.06
     Polic
    0.06
    981
    0.06
    otope
    0.06
    acos
    0.06
    NECTION
    0.06
    Activations Density 0.013%

    No Known Activations