© 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. 120132
    Prev
    Next
    INDEX
    Explanations

    references to positions or roles within academic and professional structures

    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
     Pon
    -0.06
     имÑĥ
    -0.05
    ĥĿ
    -0.05
     pur
    -0.05
    quee
    -0.05
    ¹Ħ
    -0.05
    ÃĹ↵↵
    -0.05
     copp
    -0.05
     lhs
    -0.05
     pon
    -0.05
    POSITIVE LOGITS
     R
    0.14
    ÂłR
    0.14
     र
    0.14
    $r
    0.12
    	R
    0.12
    .R
    0.12
    _R
    0.12
    _r
    0.11
    -re
    0.11
     ر
    0.11
    Activations Density 0.896%

    No Known Activations