© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88870
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "function" in programming-related text

    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
    tember
    -0.08
    laps
    -0.08
    ish
    -0.06
    atory
    -0.06
    lok
    -0.06
    .oc
    -0.06
    lic
    -0.06
    ÙĩÙĪرÛĮ
    -0.06
    ffen
    -0.06
    775
    -0.06
    POSITIVE LOGITS
    باØŃ
    0.07
     addCriterion
    0.07
    inkel
    0.07
    abant
    0.07
    erva
    0.06
    zb
    0.06
    emmel
    0.06
     ToString
    0.06
    eated
    0.06
    iage
    0.06
    Activations Density 0.003%

    No Known Activations