© 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. 14949
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    eden
    -0.08
    zung
    -0.07
    hoff
    -0.07
    este
    -0.07
    antal
    -0.07
    Rendering
    -0.07
    ningar
    -0.07
    HandlerContext
    -0.07
    osate
    -0.07
    aurant
    -0.07
    POSITIVE LOGITS
    Kit
    0.06
     double
    0.06
    Scope
    0.06
    å¯
    0.06
    озÑı
    0.06
     Kit
    0.06
    åĮ
    0.05
     squared
    0.05
    .Back
    0.05
    ÑĥÑģка
    0.05
    Activations Density 0.039%

    No Known Activations