© 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. 58902
    Prev
    Next
    INDEX
    Explanations

    references to sports events and match details

    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
     Kanun
    -0.08
    OffsetTable
    -0.08
    unar
    -0.07
    заб
    -0.07
    iddi
    -0.07
    å³
    -0.07
     Sır
    -0.07
    ÑĤаб
    -0.07
    edir
    -0.07
    asser
    -0.07
    POSITIVE LOGITS
     winner
    0.07
     idle
    0.07
    lag
    0.07
    erta
    0.06
     winners
    0.06
     fer
    0.06
     selected
    0.06
     tie
    0.06
    дÑĭ
    0.05
    ê²°
    0.05
    Activations Density 0.007%

    No Known Activations