© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 93976
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements related to navigation and user interface components

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    chat
    -0.06
    esh
    -0.06
    ropp
    -0.06
     for
    -0.06
    ist
    -0.06
    yz
    -0.06
     to
    -0.05
     Williamson
    -0.05
    j
    -0.05
    ym
    -0.05
    POSITIVE LOGITS
    ovna
    0.09
    /stdc
    0.09
    érica
    0.08
    Ïĥη
    0.08
    acular
    0.08
    rsa
    0.07
    iationException
    0.07
    GenerationStrategy
    0.07
    OLON
    0.07
    oltage
    0.07
    Activations Density 0.001%

    No Known Activations