© 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. 116961
    Prev
    Next
    INDEX
    Explanations

    themes related to community and social interactions

    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
     Listings
    -0.06
    chest
    -0.06
     Emer
    -0.06
    ãĤ¦ãĥĪ
    -0.05
     equation
    -0.05
     cogn
    -0.05
     GOODMAN
    -0.05
    Âľ
    -0.05
     America
    -0.05
     Attendance
    -0.05
    POSITIVE LOGITS
     episode
    0.07
     forthcoming
    0.07
    isons
    0.07
    ÅĻev
    0.07
    PHA
    0.07
    edis
    0.07
     session
    0.07
    zilla
    0.06
    ecome
    0.06
    mür
    0.06
    Activations Density 0.162%

    No Known Activations