© 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. 9-LLAMASCOPE-RES-131K
    11. 94179
    Prev
    Next
    INDEX
    Explanations

    references to talent and talented individuals

    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
    bons
    -0.07
    wald
    -0.07
    orget
    -0.07
    ież
    -0.07
    anter
    -0.07
    nth
    -0.07
    leston
    -0.07
    lund
    -0.07
    ordin
    -0.07
    illon
    -0.07
    POSITIVE LOGITS
    ocracy
    0.09
    à¸ĩาà¸Ļ
    0.08
    istic
    0.08
    odor
    0.07
    uous
    0.07
    ustr
    0.07
    fully
    0.07
    setter
    0.06
    ocratic
    0.06
    ä¸įåĪ°
    0.06
    Activations Density 0.011%

    No Known Activations