© 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. 14312
    Prev
    Next
    INDEX
    Explanations

    punctuation sequences, particularly focusing on sentence endings and pauses in dialogue

    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
    ecd
    -0.07
    utta
    -0.07
    vez
    -0.06
    ávÄĽ
    -0.06
     blur
    -0.06
    _DRIVE
    -0.06
    esper
    -0.06
    aeda
    -0.06
    esel
    -0.06
    arth
    -0.06
    POSITIVE LOGITS
    âĢİ
    0.07
    ifax
    0.07
    itial
    0.06
    âĢı
    0.06
    acional
    0.06
    uan
    0.06
    tring
    0.06
    decltype
    0.06
    eof
    0.06
    then
    0.06
    Activations Density 0.014%

    No Known Activations