© 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. 91792
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical dimensions and interactions with objects

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     hete
    -0.08
    (åľŁ
    -0.07
    (æĹ¥
    -0.07
    oplay
    -0.07
     dál
    -0.06
    isen
    -0.06
    ngen
    -0.06
    tro
    -0.06
    ëŀ
    -0.06
    loud
    -0.06
    POSITIVE LOGITS
     entire
    0.14
     whole
    0.10
     Entire
    0.10
    whole
    0.09
     large
    0.09
     entirety
    0.08
     larger
    0.08
    Whole
    0.07
     complex
    0.07
    macros
    0.07
    Activations Density 0.023%

    No Known Activations