© 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. 14355
    Prev
    Next
    INDEX
    Explanations

    occurrences of the acronym UPI

    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
    enheim
    -0.08
    actual
    -0.06
    Actual
    -0.06
    .emf
    -0.06
    alg
    -0.06
    ená
    -0.06
    mag
    -0.06
    bl
    -0.06
    yle
    -0.06
    nil
    -0.06
    POSITIVE LOGITS
    алиÑģÑĤ
    0.07
     IDb
    0.07
     dest
    0.06
    ften
    0.06
     reserves
    0.06
     Heath
    0.06
    å¸Į
    0.06
     تÙĤ
    0.06
    ushi
    0.06
     Spread
    0.06
    Activations Density 0.000%

    No Known Activations