© 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. 124654
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports game performances

    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
     tw
    -0.07
     tit
    -0.06
    Å¡en
    -0.06
    azı
    -0.06
     canvas
    -0.06
     genu
    -0.06
    utar
    -0.05
     holder
    -0.05
     bs
    -0.05
     fountain
    -0.05
    POSITIVE LOGITS
    ATYPE
    0.07
     Ú©ÙĪÙĩ
    0.07
    iddet
    0.07
    ÂĽ
    0.07
    itchen
    0.07
    rollers
    0.07
    orb
    0.07
    oại
    0.06
     PATCH
    0.06
    agrid
    0.06
    Activations Density 0.002%

    No Known Activations