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. 5499
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring or points in sports contexts

    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
    885
    -0.06
    rial
    -0.06
     squat
    -0.06
    IfExists
    -0.06
    ENS
    -0.06
    inkle
    -0.06
     triang
    -0.06
    830
    -0.06
    .Interop
    -0.06
    stral
    -0.06
    POSITIVE LOGITS
     difference
    0.09
     Difference
    0.07
     deficit
    0.07
     lead
    0.07
    ами
    0.07
    wen
    0.06
     advantage
    0.06
    ger
    0.06
    ãĥ³ãĥģ
    0.06
    difference
    0.06
    Activations Density 0.003%

    No Known Activations