© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 90882
    Prev
    Next
    INDEX
    Explanations

    references to competitive athletic performance and achievements

    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
    ergus
    -0.07
    unks
    -0.06
    olik
    -0.06
    isser
    -0.06
    hash
    -0.06
    iguiente
    -0.06
    ummer
    -0.06
    mk
    -0.06
    alore
    -0.06
    ampo
    -0.06
    POSITIVE LOGITS
     switched
    0.07
    ylko
    0.07
    UNUSED
    0.06
    _UNSIGNED
    0.06
     Switch
    0.06
    RGBA
    0.06
    VIC
    0.06
     switch
    0.06
     switches
    0.06
    Thrown
    0.06
    Activations Density 0.030%

    No Known Activations