© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94073
    Prev
    Next
    INDEX
    Explanations

    medical terms related to conditions, especially those affecting the arteries and fingers

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    WRAPPER
    -0.07
    illac
    -0.07
    rex
    -0.07
    oda
    -0.07
    essen
    -0.07
    onte
    -0.07
    ente
    -0.07
    æİĮ
    -0.07
    etur
    -0.07
    jerne
    -0.07
    POSITIVE LOGITS
     Weed
    0.06
     larg
    0.06
    elite
    0.06
    cies
    0.05
     definit
    0.05
     glob
    0.05
    flows
    0.05
     rect
    0.05
    kes
    0.05
    958
    0.05
    Activations Density 0.023%

    No Known Activations