© 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 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. 85749
    Prev
    Next
    INDEX
    Explanations

    elements related to software setup and configuration

    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
     Pruitt
    -0.07
    ibraltar
    -0.06
     Rubin
    -0.06
    rieg
    -0.06
    ichen
    -0.06
     Operational
    -0.06
    ofs
    -0.06
    assa
    -0.06
    äng
    -0.06
    iox
    -0.06
    POSITIVE LOGITS
     Wi
    0.07
    Wheel
    0.07
    vat
    0.07
     Fil
    0.07
    .depend
    0.06
    -webpack
    0.06
     trav
    0.06
     vit
    0.06
     Wass
    0.06
     setuptools
    0.06
    Activations Density 0.012%

    No Known Activations