© 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. 18316
    Prev
    Next
    INDEX
    Explanations

    assignment statements and expressions in code

    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
     Bray
    -0.06
     Susp
    -0.06
    unt
    -0.06
    ainer
    -0.06
    .partial
    -0.06
    errer
    -0.06
     ÑĥкÑĢаÑĹнÑģÑĮкоÑĹ
    -0.06
     Calder
    -0.06
    atoi
    -0.06
     Zimmerman
    -0.06
    POSITIVE LOGITS
    виÑĤ
    0.07
    guards
    0.06
    egasus
    0.06
    \Migration
    0.06
    IGNAL
    0.06
    Internal
    0.06
    eron
    0.06
    ARENT
    0.06
     INTERNAL
    0.06
    ses
    0.06
    Activations Density 0.009%

    No Known Activations