© 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. 81192
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "event" and its variations

    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
    innen
    -0.08
    wort
    -0.07
    ackers
    -0.07
    eres
    -0.07
    eso
    -0.07
    keit
    -0.07
    pin
    -0.07
    /el
    -0.07
    etine
    -0.07
    aret
    -0.07
    POSITIVE LOGITS
    uality
    0.18
    ually
    0.11
    uated
    0.10
    uate
    0.10
    ual
    0.09
    681
    0.09
    ful
    0.08
    ement
    0.08
    ally
    0.08
     Horizon
    0.07
    Activations Density 0.042%

    No Known Activations