© 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. 77830
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring and performance metrics in sports

    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
    zar
    -0.08
     Banc
    -0.07
     Twe
    -0.07
    èŤ
    -0.07
    amaz
    -0.07
    à¥įà¤Ĺत
    -0.07
    à¸Ĺาà¸ĩ
    -0.06
    .HTTP
    -0.06
    alı
    -0.06
    kou
    -0.06
    POSITIVE LOGITS
     attend
    0.06
    iev
    0.06
     Dunn
    0.06
     licking
    0.06
    braco
    0.06
    ymb
    0.06
    ym
    0.06
     lightly
    0.05
    peri
    0.05
    zig
    0.05
    Activations Density 0.000%

    No Known Activations