© 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. 15-LLAMASCOPE-RES-131K
    11. 88748
    Prev
    Next
    INDEX
    Explanations

    terms related to political positions and governmental roles

    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
    anou
    -0.07
     Goldberg
    -0.07
    _wheel
    -0.07
    latlong
    -0.07
    aucoup
    -0.07
    Except
    -0.07
     çIJ
    -0.07
    hart
    -0.07
    uft
    -0.07
    phis
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.07
    762
    0.06
    art
    0.06
     Crush
    0.06
    izio
    0.06
     Pro
    0.05
     classname
    0.05
     Highly
    0.05
     Rum
    0.05
     briefly
    0.05
    Activations Density 0.011%

    No Known Activations