© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1737
    Prev
    Next
    INDEX
    Explanations

    groups and quantities of players or athletes mentioned in the context of teams or 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
    NSMutable
    -0.06
     Klein
    -0.06
    ansk
    -0.06
     indeb
    -0.06
     MüdürlÃ¼ÄŁÃ¼
    -0.06
    zure
    -0.06
    .hr
    -0.06
    âĢĬ
    -0.06
    _CONNECT
    -0.06
    Fatal
    -0.06
    POSITIVE LOGITS
     whom
    0.09
     whose
    0.09
     who
    0.07
    whose
    0.07
    OCK
    0.07
    atar
    0.06
     tun
    0.06
     kteÅĻÃŃ
    0.06
    ucc
    0.06
     اÙĦØ°ÙĬÙĨ
    0.06
    Activations Density 0.037%

    No Known Activations