© 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. 95626
    Prev
    Next
    INDEX
    Explanations

    concepts related to leadership and setting examples for others

    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
    Ì
    -0.06
     sep
    -0.05
     skilled
    -0.05
    ollo
    -0.05
    \<^
    -0.05
     cons
    -0.05
     wash
    -0.05
    indr
    -0.05
    nder
    -0.05
    è©
    -0.05
    POSITIVE LOGITS
     precedent
    0.18
     preced
    0.16
    preced
    0.16
     precedence
    0.13
     trend
    0.11
     template
    0.10
    template
    0.10
    ë¡Ģ
    0.10
     пÑĢимеÑĢ
    0.09
     trail
    0.09
    Activations Density 0.118%

    No Known Activations