© 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. 116654
    Prev
    Next
    INDEX
    Explanations

    references to quantities or numbers that indicate small amounts or quantities over time

    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
    avou
    -0.07
    onium
    -0.07
    .fromString
    -0.07
    onse
    -0.07
    JI
    -0.07
    izik
    -0.07
    ouz
    -0.07
    bou
    -0.07
    edes
    -0.07
    Ñģли
    -0.06
    POSITIVE LOGITS
     months
    0.10
     hundred
    0.08
     weeks
    0.08
     years
    0.08
     dozen
    0.08
     days
    0.07
    months
    0.07
     month
    0.06
     thousand
    0.06
     ÏĩÏģÏĮνια
    0.06
    Activations Density 0.021%

    No Known Activations