© 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. 70330
    Prev
    Next
    INDEX
    Explanations

    references to degrees and angles, particularly in relation to views and perspectives

    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
    oÅĪ
    -0.08
    itive
    -0.07
    ataka
    -0.07
    /sys
    -0.07
    smith
    -0.07
    .si
    -0.07
    .Interop
    -0.07
    /testing
    -0.07
    ÅĻÃŃž
    -0.07
    лен
    -0.07
    POSITIVE LOGITS
     view
    0.10
     coverage
    0.07
    -view
    0.07
    /full
    0.07
    coverage
    0.07
     full
    0.07
    angles
    0.06
     views
    0.06
    view
    0.06
     View
    0.06
    Activations Density 0.009%

    No Known Activations