© 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. 116639
    Prev
    Next
    INDEX
    Explanations

    snippets of programming code or syntax elements

    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
    Negative Logits
    stoff
    -0.06
     Parallel
    -0.06
    729
    -0.06
     Boeh
    -0.06
    ÑĤов
    -0.06
    idon
    -0.06
     Split
    -0.06
    uga
    -0.05
     split
    -0.05
     kre
    -0.05
    POSITIVE LOGITS
     StringBuilder
    0.08
    ascar
    0.08
     Render
    0.07
    ippi
    0.07
    amba
    0.07
     dash
    0.07
    .line
    0.07
     addCriterion
    0.07
     render
    0.07
    _printf
    0.07
    Activations Density 0.066%

    No Known Activations