© 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. 62231
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to various topics of interest

    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
    czy
    -0.07
    day
    -0.06
    iferay
    -0.06
    ocode
    -0.06
    uat
    -0.06
    нÑĤ
    -0.06
    elves
    -0.06
    Blog
    -0.06
    åł±
    -0.06
    ift
    -0.06
    POSITIVE LOGITS
    PFN
    0.07
    onya
    0.07
    ież
    0.06
    ovsky
    0.06
    znam
    0.06
    alendar
    0.06
     rounding
    0.06
    /GPL
    0.06
    Separated
    0.06
    ÙĦÙĪ
    0.06
    Activations Density 0.014%

    No Known Activations