© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84763
    Prev
    Next
    INDEX
    Explanations

    references to political actions and events

    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
    .OUT
    -0.07
    uzu
    -0.07
    515
    -0.07
     кÑĢÑĥг
    -0.07
    addAction
    -0.06
    одав
    -0.06
     ç±
    -0.06
    _board
    -0.06
    ngo
    -0.06
    à¥Ĥस
    -0.06
    POSITIVE LOGITS
     tradition
    0.07
    rlen
    0.06
    acco
    0.06
     heck
    0.06
    Forge
    0.06
    ¶
    0.06
     audience
    0.06
    decor
    0.06
    Floor
    0.06
    bic
    0.06
    Activations Density 0.008%

    No Known Activations