© 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. 69226
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to definitions and interpretations of words or ideas

    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
     Bob
    -0.06
    ron
    -0.06
    mitt
    -0.06
     пÑĢоп
    -0.06
    uling
    -0.06
    els
    -0.06
    bob
    -0.06
     bob
    -0.06
    indent
    -0.05
    Bob
    -0.05
    POSITIVE LOGITS
     meaning
    0.18
     meanings
    0.16
     Meaning
    0.16
    meaning
    0.15
     usage
    0.11
    Mean
    0.11
    usage
    0.10
     ìĿĺ미
    0.10
     senses
    0.10
     Usage
    0.10
    Activations Density 0.082%

    No Known Activations