© 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. 18840
    Prev
    Next
    INDEX
    Explanations

    numerical expressions related to dates and measurements

    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
    ect
    -0.07
    ext
    -0.06
    .typ
    -0.06
     char
    -0.06
    EXT
    -0.06
     object
    -0.06
    mani
    -0.06
     Darling
    -0.05
    awah
    -0.05
    моÑĤ
    -0.05
    POSITIVE LOGITS
    kowski
    0.07
     marked
    0.07
     marks
    0.06
    marks
    0.06
    ender
    0.06
     deadline
    0.06
     بÙĪابة
    0.06
    _COLUMNS
    0.06
    appy
    0.06
    Ļ
    0.06
    Activations Density 0.028%

    No Known Activations