© 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. 119743
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance

    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
    ekler
    -0.07
    uien
    -0.07
    endir
    -0.07
    reich
    -0.07
     __("
    -0.07
    åħ¸
    -0.06
    _macros
    -0.06
     оÑĢганиза
    -0.06
    õi
    -0.06
    cgi
    -0.06
    POSITIVE LOGITS
     record
    0.08
     Record
    0.07
     RECORD
    0.07
    iness
    0.06
    upp
    0.06
    rek
    0.06
     silver
    0.06
     Falcon
    0.06
    eness
    0.06
    blast
    0.06
    Activations Density 0.013%

    No Known Activations