© 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. 9-LLAMASCOPE-RES-131K
    11. 94917
    Prev
    Next
    INDEX
    Explanations

    instances of the word "then" indicating a sequence or transition in narrative

    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
    sko
    -0.08
    bourg
    -0.07
    onya
    -0.07
    zed
    -0.07
    ']!='
    -0.07
    gger
    -0.07
    añ
    -0.07
    æĿľ
    -0.07
    amp
    -0.06
    ivent
    -0.06
    POSITIVE LOGITS
    침
    0.07
    TURE
    0.06
    rez
    0.06
    VRT
    0.06
    egative
    0.06
    çŁ¢
    0.06
     geçen
    0.06
    inson
    0.06
    bÃŃ
    0.06
    IFIER
    0.06
    Activations Density 0.014%

    No Known Activations