© 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. 5236
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and references to mathematical concepts

    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
     propositions
    -0.06
     Blueprint
    -0.06
    inks
    -0.06
    oucher
    -0.06
    lesi
    -0.06
     Rai
    -0.05
     Cust
    -0.05
    564
    -0.05
    _multi
    -0.05
    ailer
    -0.05
    POSITIVE LOGITS
    _codegen
    0.08
    elerik
    0.08
    rowsable
    0.07
    veau
    0.07
    uyên
    0.07
    ÑĢож
    0.07
    bdd
    0.07
    smooth
    0.07
    integral
    0.07
    _blocking
    0.07
    Activations Density 0.031%

    No Known Activations