© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14407
    Prev
    Next
    INDEX
    Explanations

    mentions of events and the participation of individuals in those 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
    omba
    -0.07
    rana
    -0.06
    ihu
    -0.06
    ysa
    -0.06
    ä¿¡
    -0.06
    agara
    -0.06
     Mein
    -0.06
    ena
    -0.06
    ugen
    -0.06
     Hag
    -0.06
    POSITIVE LOGITS
    endcode
    0.08
    HeaderCode
    0.07
     afin
    0.07
     nhằm
    0.07
    /gtest
    0.07
    513
    0.07
    redient
    0.07
    _exempt
    0.07
    VisualStyle
    0.06
    CodeAt
    0.06
    Activations Density 0.027%

    No Known Activations