© 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 EvalsExportsAPI 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. 125637
    Prev
    Next
    INDEX
    Explanations

    topics related to social dynamics and emotional skills

    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
     èĢ
    -0.09
    enef
    -0.08
    echan
    -0.07
    ogan
    -0.07
    asant
    -0.07
    enso
    -0.07
    arget
    -0.07
    ERSIST
    -0.07
     HttpServlet
    -0.07
    untas
    -0.07
    POSITIVE LOGITS
    /social
    0.08
     observational
    0.06
     Hier
    0.06
     social
    0.06
    oley
    0.06
     networking
    0.06
     Social
    0.06
     interaction
    0.06
    -social
    0.06
     vars
    0.06
    Activations Density 0.013%

    No Known Activations