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

    Neuronpedia

    APICircuit 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. 5719
    Prev
    Next
    INDEX
    Explanations

    references to baseball actions and player interactions

    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
     outs
    -0.07
    undy
    -0.07
    uner
    -0.06
    eros
    -0.06
    ury
    -0.06
    .edu
    -0.06
    ufe
    -0.06
    tero
    -0.06
    awan
    -0.06
     Inn
    -0.06
    POSITIVE LOGITS
    ãĤ
    0.07
    ARB
    0.07
    eyer
    0.06
    ymes
    0.06
     swing
    0.06
     swinging
    0.06
    aths
    0.06
    代
    0.06
    abinet
    0.06
    -guide
    0.06
    Activations Density 0.005%

    No Known Activations