© 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. 9-LLAMASCOPE-RES-131K
    11. 94121
    Prev
    Next
    INDEX
    Explanations

    the word "also" and its equivalents in different languages

    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
    subcategory
    -0.07
    454
    -0.07
    anne
    -0.06
    inner
    -0.06
    оло
    -0.06
    farm
    -0.06
    429
    -0.06
    edis
    -0.06
    uat
    -0.06
     Industries
    -0.06
    POSITIVE LOGITS
     Punch
    0.08
    burgh
    0.07
    egral
    0.07
    uzu
    0.07
    ugin
    0.07
    APT
    0.07
    elyn
    0.07
     uncert
    0.07
     punched
    0.07
    awning
    0.06
    Activations Density 0.000%

    No Known Activations