© 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. 63027
    Prev
    Next
    INDEX
    Explanations

    structured data elements in code snippets

    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
    ulet
    -0.07
    ague
    -0.07
    arch
    -0.06
     bin
    -0.06
    ummer
    -0.06
    .dispatcher
    -0.06
    ycl
    -0.06
    .KeyPress
    -0.06
    older
    -0.06
    ubi
    -0.06
    POSITIVE LOGITS
    ione
    0.07
    dech
    0.07
    ovsky
    0.07
    quisa
    0.06
    _HOT
    0.06
    UsageId
    0.06
    \grid
    0.06
     CActive
    0.06
    OfSize
    0.06
    .NoSuch
    0.06
    Activations Density 0.000%

    No Known Activations