© 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. 17-LLAMASCOPE-RES-131K
    11. 55489
    Prev
    Next
    INDEX
    Explanations

    information related to sports and player 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
    вок
    -0.07
    ãĥ³ãĥIJ
    -0.07
    анов
    -0.07
    iones
    -0.06
    poi
    -0.06
    hos
    -0.06
    пов
    -0.06
    *scale
    -0.06
    viar
    -0.06
    Cpp
    -0.06
    POSITIVE LOGITS
     debut
    0.09
     immediately
    0.09
     settling
    0.09
     joining
    0.09
     arrival
    0.09
     instantly
    0.08
     introdu
    0.08
     fit
    0.08
     Orientation
    0.08
    joining
    0.08
    Activations Density 0.026%

    No Known Activations