© 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. 69421
    Prev
    Next
    INDEX
    Explanations

    terms related to various physical conditions and their effects

    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
    agger
    -0.08
    emes
    -0.06
     Soda
    -0.06
    awe
    -0.06
    ymes
    -0.06
    ernaut
    -0.06
    core
    -0.06
     Weed
    -0.06
    verb
    -0.06
     deg
    -0.05
    POSITIVE LOGITS
    baugh
    0.07
    .mime
    0.06
     tack
    0.06
     Voj
    0.06
    .application
    0.06
    neh
    0.06
     drying
    0.06
     application
    0.06
    atır
    0.06
    reh
    0.06
    Activations Density 0.004%

    No Known Activations