© 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. 17-LLAMASCOPE-RES-131K
    11. 70724
    Prev
    Next
    INDEX
    Explanations

    references to sports awards and accolades

    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
     Ãľl
    -0.07
    anca
    -0.07
    aggi
    -0.07
    rame
    -0.07
    ocket
    -0.06
    оÑģк
    -0.06
    bas
    -0.06
    178
    -0.06
    ecd
    -0.06
    andbox
    -0.06
    POSITIVE LOGITS
    0.07
    .LoggerFactory
    0.07
    icensed
    0.06
    timeofday
    0.06
    quam
    0.06
    gnore
    0.06
    illas
    0.06
    ous
    0.06
    [in
    0.06
     Kle
    0.06
    Activations Density 0.020%

    No Known Activations