© 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. 69405
    Prev
    Next
    INDEX
    Explanations

    variations of the root word "stress"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Encoding
    -0.07
    ird
    -0.06
    éné
    -0.06
    oles
    -0.06
    ushing
    -0.06
    oom
    -0.06
     ÏĥÏĦα
    -0.06
    ees
    -0.06
    ison
    -0.06
    zial
    -0.06
    POSITIVE LOGITS
    ngthen
    0.08
    gth
    0.08
    icher
    0.08
    ãĥ¼ãĥŃ
    0.08
    licht
    0.07
    wart
    0.07
    /testify
    0.07
    åĭĻ
    0.07
    (Str
    0.07
    اسب
    0.06
    Activations Density 0.006%

    No Known Activations