© 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. 69127
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and 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
    ëľ
    -0.07
     Bin
    -0.06
     Pac
    -0.06
    alin
    -0.06
    HELL
    -0.06
     Modern
    -0.06
     पड
    -0.06
    ynn
    -0.06
    Bin
    -0.06
     masking
    -0.06
    POSITIVE LOGITS
     final
    0.12
     finish
    0.11
     Final
    0.10
     finalize
    0.10
    finish
    0.10
     finished
    0.10
    final
    0.10
     completion
    0.10
    Final
    0.10
     FINAL
    0.10
    Activations Density 0.081%

    No Known Activations