© 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. 108749
    Prev
    Next
    INDEX
    Explanations

    limits and regulations on quantities or amounts

    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
    alone
    -0.07
    .sd
    -0.06
    eyi
    -0.06
    eyin
    -0.06
    ninger
    -0.06
    åĿ¦
    -0.06
    γκ
    -0.06
    rades
    -0.06
    usa
    -0.06
     Patreon
    -0.06
    POSITIVE LOGITS
     limit
    0.17
     limits
    0.17
     maximum
    0.15
     Limit
    0.15
    limit
    0.15
     Limits
    0.15
     limitation
    0.14
     LIMIT
    0.14
    limits
    0.14
     limitations
    0.14
    Activations Density 0.036%

    No Known Activations