© 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. 123497
    Prev
    Next
    INDEX
    Explanations

    measurements and specifications related to construction or material details

    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
    iez
    -0.07
    idge
    -0.07
    oad
    -0.06
    HITE
    -0.06
    è¼Ŀ
    -0.06
     Gale
    -0.06
    fried
    -0.06
     Controller
    -0.06
    iscard
    -0.06
    éĻį
    -0.06
    POSITIVE LOGITS
     conversions
    0.08
    conversion
    0.08
    units
    0.07
    :convert
    0.07
    onom
    0.07
     Converted
    0.07
     converter
    0.07
    Ñģи
    0.07
    usercontent
    0.07
     conversion
    0.07
    Activations Density 0.011%

    No Known Activations