© 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. 104431
    Prev
    Next
    INDEX
    Explanations

    specific biological terms related to anatomical structures and classifications

    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
    ftar
    -0.07
    Cop
    -0.07
    ectar
    -0.06
    allet
    -0.06
    stial
    -0.06
    ialis
    -0.06
     famously
    -0.06
    -0.06
    деÑĤ
    -0.06
    inel
    -0.06
    POSITIVE LOGITS
    kee
    0.07
     Kear
    0.07
    ç½®
    0.06
    /*/
    0.06
    æµľ
    0.06
     Weinstein
    0.06
    quette
    0.06
    ŀ
    0.06
    /unit
    0.06
    \Events
    0.06
    Activations Density 0.001%

    No Known Activations