© 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. 69315
    Prev
    Next
    INDEX
    Explanations

    references to physical impacts and collisions 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
    문ìĿĦ
    -0.07
    _INS
    -0.06
    otti
    -0.06
     skips
    -0.06
    sein
    -0.06
    gov
    -0.06
    ัมà¸ŀ
    -0.06
    aney
    -0.06
    ambda
    -0.06
    ocale
    -0.06
    POSITIVE LOGITS
    riel
    0.07
     Violence
    0.07
    rosse
    0.06
    Intent
    0.06
    &view
    0.06
    etooth
    0.06
     contato
    0.06
    693
    0.06
    /tos
    0.06
    .getTarget
    0.06
    Activations Density 0.024%

    No Known Activations