© 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. 78470
    Prev
    Next
    INDEX
    Explanations

    references to organizational or governmental structures, particularly those related to service delivery or administrative functions

    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
    iscard
    -0.08
    ↵↵
    -0.08
    acha
    -0.08
    ewan
    -0.07
     Mast
    -0.07
    Ñĵ
    -0.07
    eneg
    -0.07
    imers
    -0.06
    yne
    -0.06
    UMB
    -0.06
    POSITIVE LOGITS
     Vik
    0.07
    ore
    0.07
    /body
    0.07
    ç¦
    0.07
    orno
    0.06
    æµ´
    0.06
    geh
    0.06
    γκο
    0.06
    ey
    0.06
    gate
    0.06
    Activations Density 0.011%

    No Known Activations