© 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. 5883
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and programming structures

    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
     rencontre
    -0.06
    airo
    -0.06
     Smithsonian
    -0.06
    ialis
    -0.06
    ิà¸Ĺย
    -0.06
     Miscellaneous
    -0.06
     amo
    -0.06
     Willis
    -0.05
     Skeleton
    -0.05
     Lad
    -0.05
    POSITIVE LOGITS
    :start
    0.07
    hte
    0.07
    edir
    0.07
    zem
    0.06
    HeaderCode
    0.06
     noqa
    0.06
     creampie
    0.06
     commence
    0.06
    ongsTo
    0.06
    agar
    0.06
    Activations Density 0.043%

    No Known Activations