© 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. 89212
    Prev
    Next
    INDEX
    Explanations

    terms related to injuries and health issues 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
    stitutions
    -0.08
     Fell
    -0.06
    idget
    -0.06
    -wide
    -0.06
    å¼¥
    -0.06
     organs
    -0.06
    hte
    -0.06
    eking
    -0.06
     naš
    -0.06
    Informe
    -0.06
    POSITIVE LOGITS
    abyrin
    0.08
    edl
    0.07
    ilig
    0.07
     Fortune
    0.07
    oque
    0.06
    owied
    0.06
    arkan
    0.06
    oop
    0.06
    yped
    0.06
    Occurred
    0.06
    Activations Density 0.011%

    No Known Activations