© 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. 53763
    Prev
    Next
    INDEX
    Explanations

    specific attributes and measurements related to objects and components

    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
     literal
    -0.06
     abdom
    -0.06
    330
    -0.06
     bas
    -0.06
    -0.06
    ás
    -0.06
     woll
    -0.06
    491
    -0.06
     mys
    -0.06
    :
    -0.06
    POSITIVE LOGITS
    kova
    0.08
     OTHERWISE
    0.08
     ãĤŃãĥ£
    0.08
    виÑī
    0.08
    riott
    0.08
    educt
    0.07
     Yani
    0.07
    ιÏĩ
    0.07
     Hlav
    0.07
    esco
    0.07
    Activations Density 0.047%

    No Known Activations