© 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. 80164
    Prev
    Next
    INDEX
    Explanations

    references to regulations and their enactment dates

    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
    -selection
    -0.06
    toa
    -0.06
     announcements
    -0.06
    amik
    -0.06
    oen
    -0.06
    _MOD
    -0.06
    ÑĨин
    -0.06
     cir
    -0.06
     ANN
    -0.06
    oard
    -0.06
    POSITIVE LOGITS
    artial
    0.07
    ucha
    0.06
    isky
    0.06
     deadline
    0.06
     implementation
    0.06
    atta
    0.06
    usher
    0.06
    esco
    0.06
     ìĭľíĸī
    0.06
    elper
    0.06
    Activations Density 0.066%

    No Known Activations