© 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. 116532
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns of punctuation and symbols

    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
    jvu
    -0.09
     Eins
    -0.07
    ÏĦÏģι
    -0.07
    ucch
    -0.06
    onth
    -0.06
    ovu
    -0.06
     ÑģкладÑĸ
    -0.06
    ÑĤÑĢо
    -0.06
    lesi
    -0.06
    cplusplus
    -0.06
    POSITIVE LOGITS
    ange
    0.06
     Gallagher
    0.06
     Bingo
    0.06
     Clar
    0.06
    ragment
    0.06
     Rage
    0.06
     cas
    0.06
    rats
    0.06
    ihar
    0.06
    ssize
    0.06
    Activations Density 0.002%

    No Known Activations