© 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. 59161
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental actions and their intended effects

    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
    actionDate
    -0.07
    owers
    -0.07
    utschen
    -0.06
    pll
    -0.06
    меÑĩ
    -0.06
    ädchen
    -0.06
    £i
    -0.06
    affer
    -0.06
    ardon
    -0.06
    दम
    -0.06
    POSITIVE LOGITS
     transparent
    0.07
    orny
    0.07
     st
    0.06
    æijĨ
    0.06
    era
    0.06
    olves
    0.06
    olatile
    0.06
     moll
    0.06
     Banks
    0.06
     vex
    0.06
    Activations Density 0.031%

    No Known Activations