© 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. 2694
    Prev
    Next
    INDEX
    Explanations

    occurrences of function definitions and method calls 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
    ylko
    -0.07
    PLAIN
    -0.07
    été
    -0.07
    bish
    -0.06
    èī²çļĦ
    -0.06
    arden
    -0.06
    herits
    -0.06
    ÑģиÑħ
    -0.06
    ÑĤиÑĢов
    -0.06
    azu
    -0.06
    POSITIVE LOGITS
     getArguments
    0.07
    orrent
    0.07
     arguments
    0.07
    546
    0.07
    929
    0.07
    arguments
    0.07
    ghan
    0.07
    (arguments
    0.07
     Trend
    0.07
    args
    0.06
    Activations Density 0.006%

    No Known Activations