© 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. 15-LLAMASCOPE-RES-131K
    11. 27437
    Prev
    Next
    INDEX
    Explanations

    statistical performance metrics related to athletes or teams 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
     CDs
    -0.06
    iag
    -0.06
    ieur
    -0.06
    nip
    -0.06
    uç
    -0.06
     Rack
    -0.06
     Ellis
    -0.06
    oir
    -0.06
    ASC
    -0.06
    ixed
    -0.06
    POSITIVE LOGITS
    emu
    0.07
    sko
    0.06
    awai
    0.06
     beste
    0.06
    obic
    0.06
    ForObject
    0.06
     monet
    0.06
    kom
    0.06
    issant
    0.06
    jee
    0.06
    Activations Density 0.023%

    No Known Activations