© 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 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. 130287
    Prev
    Next
    INDEX
    Explanations

    statistics and comparisons related to sports performance

    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
    icros
    -0.07
    ÑĩиÑģ
    -0.07
    antity
    -0.07
    orio
    -0.07
    .Entities
    -0.07
    ictim
    -0.07
    ãn
    -0.06
    .tech
    -0.06
    ÏĦον
    -0.06
     ?><?
    -0.06
    POSITIVE LOGITS
     Perf
    0.07
     Bever
    0.07
    ookie
    0.06
     performance
    0.06
     performances
    0.06
    ника
    0.06
    Å
    0.06
    uty
    0.06
     pairwise
    0.05
     Flip
    0.05
    Activations Density 0.005%

    No Known Activations