© 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. 108917
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gold" and variations of it in various contexts

    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
    ults
    -0.08
    ãĥ¡ãĥ³ãĥĪ
    -0.07
    ulp
    -0.06
    ester
    -0.06
    uers
    -0.06
    ivalence
    -0.06
    湿
    -0.06
    ationale
    -0.06
    dire
    -0.06
    dra
    -0.06
    POSITIVE LOGITS
    fish
    0.09
    stein
    0.09
     Nug
    0.08
    mine
    0.08
    ridge
    0.08
    hab
    0.07
    wyn
    0.07
    iola
    0.07
    berg
    0.07
    finger
    0.07
    Activations Density 0.006%

    No Known Activations