© 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. 80773
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to spatial representations and dimensional structures

    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
    Contours
    -0.07
     diagonal
    -0.06
    weis
    -0.06
     zby
    -0.06
     Olympic
    -0.06
    اÙħÛĮÙĨ
    -0.06
    åı¬
    -0.06
     Slice
    -0.06
    _cells
    -0.06
    Gain
    -0.06
    POSITIVE LOGITS
     points
    0.14
     Points
    0.13
    points
    0.11
    -points
    0.11
    Points
    0.10
     point
    0.10
     puntos
    0.10
     Point
    0.09
    .Points
    0.09
     ÑĤоÑĩки
    0.09
    Activations Density 0.424%

    No Known Activations