© 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. 53806
    Prev
    Next
    INDEX
    Explanations

    references to specific technological products and their features

    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
     ilma
    -0.06
    Ùģر
    -0.06
    bern
    -0.06
    èĤī
    -0.06
    inis
    -0.06
    gere
    -0.06
    adaÅŁ
    -0.06
    lut
    -0.06
    NX
    -0.06
    оки
    -0.06
    POSITIVE LOGITS
     earlier
    0.12
     previous
    0.11
     previously
    0.11
     which
    0.10
    previous
    0.09
     Previous
    0.08
    Previous
    0.08
     Earlier
    0.07
    which
    0.07
     preceding
    0.07
    Activations Density 0.070%

    No Known Activations