© 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. 1237
    Prev
    Next
    INDEX
    Explanations

    references to events and their handling in 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
    717
    -0.06
    erus
    -0.06
    718
    -0.06
    кеÑĤ
    -0.06
    bia
    -0.06
    dna
    -0.05
     validationResult
    -0.05
    alat
    -0.05
    ãĥ«ãĥĪ
    -0.05
    okit
    -0.05
    POSITIVE LOGITS
    íĦ°
    0.07
    WithValue
    0.07
    NECT
    0.07
    imir
    0.07
    جر
    0.06
    /libs
    0.06
    ç¾½
    0.06
    YTE
    0.06
    Converter
    0.06
    mong
    0.06
    Activations Density 0.002%

    No Known Activations