© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38585
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and movements 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
    ãĥĥãĥĦ
    -0.08
    baru
    -0.08
    indre
    -0.07
    CHANT
    -0.07
    orz
    -0.07
    ãĤ«ãĥĨãĤ´ãĥª
    -0.07
    anke
    -0.07
    COPE
    -0.07
    izard
    -0.07
    ayi
    -0.07
    POSITIVE LOGITS
     teammate
    0.07
     nich
    0.06
     someone
    0.06
    ering
    0.06
    eb
    0.06
     brother
    0.06
     fellow
    0.06
     Loves
    0.06
    out
    0.06
    É
    0.06
    Activations Density 0.016%

    No Known Activations