© 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. 72523
    Prev
    Next
    INDEX
    Explanations

    elements that contribute to essential knowledge and wisdom in the context of community health and justice-related literature

    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
    uder
    -0.07
    lotte
    -0.07
    anel
    -0.07
    odor
    -0.06
     weather
    -0.06
    TTY
    -0.06
     begin
    -0.06
    adro
    -0.06
     ultimate
    -0.06
     Weather
    -0.06
    POSITIVE LOGITS
    ONGL
    0.08
    åľ¨çº¿éĺħ读
    0.07
    åĩºçīĪ社
    0.07
     ÑĢÑĥк
    0.07
     book
    0.07
    ingleton
    0.07
    izia
    0.07
    .Reader
    0.07
    book
    0.07
     overdue
    0.06
    Activations Density 0.005%

    No Known Activations