© 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. 17-LLAMASCOPE-RES-131K
    11. 38259
    Prev
    Next
    INDEX
    Explanations

    instances of transformation or rendering mentions within a programming context

    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
    ffect
    -0.07
    ffects
    -0.07
    ymous
    -0.07
    iosa
    -0.07
    hood
    -0.07
    lyphicon
    -0.06
    elfast
    -0.06
    fter
    -0.06
     èĴ
    -0.06
    oplayer
    -0.06
    POSITIVE LOGITS
    ors
    0.10
    ussen
    0.08
    ations
    0.08
    ers
    0.08
    orb
    0.07
    -origin
    0.07
    tester
    0.07
    able
    0.07
    raction
    0.07
    ersen
    0.06
    Activations Density 0.010%

    No Known Activations