© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 94976
    Prev
    Next
    INDEX
    Explanations

    information regarding celebrities' physical attributes

    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
    umont
    -0.07
    awl
    -0.07
    issy
    -0.06
    à¥įरà¤ļ
    -0.06
    Migration
    -0.06
    ĶĦ
    -0.06
    verity
    -0.06
    RefPtr
    -0.06
    leaflet
    -0.06
    .getMap
    -0.06
    POSITIVE LOGITS
    ooks
    0.08
     body
    0.08
    411
    0.07
     Measurements
    0.07
     measurement
    0.07
     Mediterranean
    0.07
    body
    0.07
     height
    0.07
     measurements
    0.07
     weight
    0.07
    Activations Density 0.003%

    No Known Activations