© 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. 91523
    Prev
    Next
    INDEX
    Explanations

    references to the concept of writing and inscriptions

    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
    uentes
    -0.06
    lington
    -0.06
    âĶĢ
    -0.06
    ãĥ¼ãĥį
    -0.06
    enson
    -0.06
    245
    -0.06
    æĶ¯
    -0.06
    AWN
    -0.06
    ÅŁt
    -0.06
    ategies
    -0.05
    POSITIVE LOGITS
    junction
    0.07
     Yug
    0.07
    anim
    0.06
    Ìĥ
    0.06
    iot
    0.06
    pun
    0.06
    igte
    0.06
    imony
    0.06
    ancock
    0.06
    chia
    0.06
    Activations Density 0.010%

    No Known Activations