© 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. 14216
    Prev
    Next
    INDEX
    Explanations

    technical terms and associated coding functions

    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
    weet
    -0.06
    oli
    -0.06
     nomin
    -0.06
     penalties
    -0.06
     Ped
    -0.05
     blur
    -0.05
     piled
    -0.05
     retro
    -0.05
    .snap
    -0.05
    enberg
    -0.05
    POSITIVE LOGITS
     replacement
    0.12
     replacements
    0.12
     Replacement
    0.11
    _replace
    0.11
     placeholders
    0.11
    replacement
    0.10
     variables
    0.10
     substitutions
    0.10
     substitution
    0.10
     template
    0.10
    Activations Density 0.176%

    No Known Activations