© 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. 79874
    Prev
    Next
    INDEX
    Explanations

    references to sports events and teams, particularly related to Polish athletes

    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
    วล
    -0.07
    ;set
    -0.07
    onde
    -0.07
    entine
    -0.07
     golf
    -0.07
     Orr
    -0.07
    ãĥ³ãĥģ
    -0.06
    burgh
    -0.06
    apur
    -0.06
    zet
    -0.06
    POSITIVE LOGITS
     regist
    0.07
    IVO
    0.07
     Energ
    0.06
    гал
    0.06
    eview
    0.06
    rap
    0.06
    Roz
    0.06
    cel
    0.06
    иной
    0.06
    çİ»çĴĥ
    0.06
    Activations Density 0.002%

    No Known Activations