© 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. 30580
    Prev
    Next
    INDEX
    Explanations

    events related to sports or crime incidents

    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
    uzey
    -0.07
    ancode
    -0.06
    hta
    -0.06
     Thief
    -0.06
    .cls
    -0.06
    меÑĩ
    -0.06
    æijĩ
    -0.06
    اÙģÙĬ
    -0.06
    Ø´ÙĨ
    -0.06
    illiseconds
    -0.06
    POSITIVE LOGITS
     yesterday
    0.07
     Mrs
    0.07
    Mrs
    0.07
    isphere
    0.07
    phas
    0.07
    PUTE
    0.07
    ounge
    0.06
    nde
    0.06
    uhe
    0.06
    .BackgroundImage
    0.06
    Activations Density 0.112%

    No Known Activations