© 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. 94138
    Prev
    Next
    INDEX
    Explanations

    the word "this."

    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
    ebra
    -0.07
    curity
    -0.06
    otyp
    -0.06
     jenter
    -0.06
    reesome
    -0.06
    uesta
    -0.06
    ìĭĿ
    -0.06
    rych
    -0.06
    pipe
    -0.06
    ìĸ¼
    -0.06
    POSITIVE LOGITS
    iteral
    0.07
     Kaplan
    0.06
    qn
    0.06
    qml
    0.06
    ars
    0.06
    ç´
    0.06
    ((-
    0.06
    ECT
    0.06
     اÙĦصÙģ
    0.06
    _sdk
    0.06
    Activations Density 0.000%

    No Known Activations