© 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. 41884
    Prev
    Next
    INDEX
    Explanations

    descriptors related to people and their roles or qualities

    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
    edis
    -0.06
    تÙĤ
    -0.06
    åķ
    -0.06
    ohana
    -0.06
     æº
    -0.06
    еÑģÑĤо
    -0.06
    adol
    -0.06
    elsing
    -0.05
     Seats
    -0.05
    ipple
    -0.05
    POSITIVE LOGITS
     himself
    0.10
    ä¸Ģ人
    0.07
     fit
    0.07
     Himself
    0.07
     whom
    0.07
    ä¸Ģ个人
    0.07
     somebody
    0.07
     someone
    0.07
    |#
    0.07
     figure
    0.07
    Activations Density 0.053%

    No Known Activations