© 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. 93246
    Prev
    Next
    INDEX
    Explanations

    names and mentions of historical figures or scholars

    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
    bote
    -0.10
    iversit
    -0.08
    ceb
    -0.08
     dikke
    -0.08
    ungle
    -0.08
    rung
    -0.07
    emez
    -0.07
    hir
    -0.07
     tiener
    -0.07
    lesia
    -0.07
    POSITIVE LOGITS
     Dutch
    0.20
     Netherlands
    0.19
    .nl
    0.16
     Amsterdam
    0.16
     van
    0.14
     Holland
    0.14
     Nederland
    0.13
     Gron
    0.13
     Rotterdam
    0.12
     Van
    0.12
    Activations Density 0.185%

    No Known Activations