© 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. 16977
    Prev
    Next
    INDEX
    Explanations

    references to injuries and their impact on players' performance

    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
    agg
    -0.07
    eniable
    -0.07
    ();)
    -0.07
    oran
    -0.06
    acock
    -0.06
    ieten
    -0.06
    .Companion
    -0.06
    ีà¹Ģà¸Ķ
    -0.06
    gid
    -0.06
    arkin
    -0.06
    POSITIVE LOGITS
     career
    0.07
     Careers
    0.07
     Career
    0.07
    üven
    0.07
    jee
    0.07
    eat
    0.06
    cke
    0.06
     careers
    0.06
    ertz
    0.06
    Career
    0.06
    Activations Density 0.016%

    No Known Activations