© 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. 61429
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    his
    -0.07
    roids
    -0.07
     Stad
    -0.07
    rech
    -0.07
    roys
    -0.06
    ovid
    -0.06
    urtle
    -0.06
    trad
    -0.06
    -Origin
    -0.06
    remen
    -0.06
    POSITIVE LOGITS
    stoup
    0.07
    /question
    0.07
    ÏĢÎŃ
    0.06
    vanished
    0.06
     moth
    0.06
     mah
    0.06
    itial
    0.06
    ì¹
    0.06
    @ResponseBody
    0.06
     Sob
    0.06
    Activations Density 0.000%

    No Known Activations