© 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. 117178
    Prev
    Next
    INDEX
    Explanations

    key moments and player names in sports events

    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
     Spin
    -0.06
    anut
    -0.06
    rette
    -0.06
    sez
    -0.06
    Äĥr
    -0.06
    زة
    -0.06
    zell
    -0.06
    xef
    -0.06
    fel
    -0.06
     surv
    -0.06
    POSITIVE LOGITS
     another
    0.10
     further
    0.10
     additional
    0.08
    another
    0.08
     weitere
    0.08
     weiter
    0.07
     dalÅ¡ÃŃ
    0.07
     thêm
    0.07
     dalÅ¡ÃŃch
    0.07
    è¿Ľä¸ĢæŃ¥
    0.07
    Activations Density 0.014%

    No Known Activations