© 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. 62511
    Prev
    Next
    INDEX
    Explanations

    references to different types or categories within a given context

    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
    onna
    -0.07
    гÑĥ
    -0.07
     nebu
    -0.07
    andest
    -0.07
    asion
    -0.06
    iques
    -0.06
    кÑĥÑĢ
    -0.06
    æĸ¹éĿ¢
    -0.06
    amet
    -0.06
    ÙģØ´
    -0.06
    POSITIVE LOGITS
    /types
    0.09
     of
    0.08
    etting
    0.07
    udson
    0.07
    /all
    0.06
    isini
    0.06
    /type
    0.06
    jac
    0.06
    Calibri
    0.06
    Verdana
    0.06
    Activations Density 0.019%

    No Known Activations