© 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. 120311
    Prev
    Next
    INDEX
    Explanations

    words related to experimental procedures and measurements in a scientific context

    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
    enson
    -0.07
    plen
    -0.07
    lectron
    -0.07
     pathMatch
    -0.06
     HOLDER
    -0.06
    ób
    -0.06
    visa
    -0.06
    HOLDER
    -0.06
    urette
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
     culture
    0.07
     Culture
    0.07
     Cell
    0.07
     Gef
    0.06
     cell
    0.06
    [block
    0.06
     cells
    0.06
    cell
    0.06
     cultures
    0.06
     either
    0.06
    Activations Density 0.059%

    No Known Activations