© 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. 120841
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its actions or presence in various contexts

    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
    apore
    -0.06
    apult
    -0.06
    _IL
    -0.06
    rello
    -0.06
    ilm
    -0.06
    edia
    -0.06
    nel
    -0.06
    Ģë¡ľ
    -0.06
    ØŃداث
    -0.06
    lius
    -0.06
    POSITIVE LOGITS
     compatibility
    0.06
     Diy
    0.06
    readcr
    0.06
     Compatibility
    0.06
    eneric
    0.06
    Pie
    0.06
    .consume
    0.06
    pytest
    0.06
    жÑĥ
    0.06
    DOI
    0.06
    Activations Density 0.024%

    No Known Activations