© 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. 72958
    Prev
    Next
    INDEX
    Explanations

    references to political actions and responses

    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
    è«ĩ
    -0.07
    ffffffff
    -0.07
    ห
    -0.07
     aras
    -0.07
    ë¹Į
    -0.06
    ilon
    -0.06
     Truy
    -0.06
    513
    -0.06
    hlen
    -0.06
    лÑĭ
    -0.06
    POSITIVE LOGITS
     Immigration
    0.08
     immigration
    0.08
     Imm
    0.08
    Imm
    0.08
    airport
    0.07
     airport
    0.07
     airlines
    0.07
     Pacific
    0.07
    aldo
    0.07
     mult
    0.07
    Activations Density 0.004%

    No Known Activations