© 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. 129976
    Prev
    Next
    INDEX
    Explanations

    specific teams and sports events information

    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
    emer
    -0.07
    -in
    -0.06
    ingly
    -0.06
    etto
    -0.06
     interaction
    -0.06
    inge
    -0.06
     between
    -0.05
    aro
    -0.05
     train
    -0.05
    лин
    -0.05
    POSITIVE LOGITS
    /Dk
    0.07
    ozem
    0.07
    (æ°´
    0.07
    _Cmd
    0.07
    adratic
    0.07
     odv
    0.07
    /Peak
    0.07
     odak
    0.07
    OfSize
    0.07
     eoq
    0.07
    Activations Density 0.020%

    No Known Activations