© 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. 108818
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically question marks and periods

    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
    berger
    -0.07
    y
    -0.06
    ake
    -0.06
     läng
    -0.06
    erman
    -0.06
    iest
    -0.06
    ya
    -0.05
    dog
    -0.05
    екÑĥ
    -0.05
    ua
    -0.05
    POSITIVE LOGITS
    acci
    0.07
    elper
    0.07
    Äįin
    0.07
    죽
    0.07
    yclopedia
    0.07
     Gaw
    0.07
    ghi
    0.07
    GRID
    0.07
    ibase
    0.07
    ãĥ¢ãĥ³
    0.07
    Activations Density 0.001%

    No Known Activations