© 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. 17-LLAMASCOPE-RES-131K
    11. 91858
    Prev
    Next
    INDEX
    Explanations

    statements about function outcomes and conditions

    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
     Renders
    -0.08
     Cooke
    -0.08
     Initializes
    -0.07
     Uncomment
    -0.06
     Initialise
    -0.06
     Jay
    -0.06
    æľĹ
    -0.06
    ib
    -0.06
     Invalidate
    -0.06
     каÑģ
    -0.06
    POSITIVE LOGITS
     caller
    0.07
    Caller
    0.07
    zek
    0.07
     Note
    0.06
     Caller
    0.06
     return
    0.06
    conciliation
    0.06
    ë²Ķ
    0.06
    mez
    0.06
     unitOfWork
    0.06
    Activations Density 0.041%

    No Known Activations