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. 31-LLAMASCOPE-RES-131K
    6. 44078
    Prev
    Next
    INDEX
    Explanations

    terms related to golf and golfing events

    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
    uais
    -0.07
    c
    -0.07
    .Îł
    -0.07
    cit
    -0.07
    tty
    -0.06
    t
    -0.06
    lopedia
    -0.06
    e
    -0.06
    fc
    -0.06
    pch
    -0.06
    POSITIVE LOGITS
    box
    0.12
     box
    0.12
    boxes
    0.12
     shot
    0.12
    -box
    0.12
    pee
    0.11
     boxes
    0.11
    -shot
    0.11
     shots
    0.10
    shot
    0.10
    Activations Density 0.004%

    No Known Activations