Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5373
    Prev
    Next
    INDEX
    Explanations

    references to sports positions and player statistics

    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
    tfoot
    -0.08
    हल
    -0.08
    ivec
    -0.08
    )((((
    -0.07
    isoft
    -0.07
    orsi
    -0.07
    vod
    -0.07
    uddy
    -0.07
    /cache
    -0.07
    asel
    -0.07
    POSITIVE LOGITS
     tight
    0.09
     Tight
    0.07
     middle
    0.07
     linebacker
    0.07
     auxiliary
    0.07
     receiver
    0.07
     utility
    0.07
     WR
    0.07
     backup
    0.06
     CB
    0.06
    Activations Density 0.026%

    No Known Activations