© 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. 80742
    Prev
    Next
    INDEX
    Explanations

    code structures and programming syntax elements

    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
     sh
    -0.06
    ropol
    -0.06
    kdir
    -0.06
    rag
    -0.06
     missing
    -0.05
    alem
    -0.05
     riff
    -0.05
     fing
    -0.05
    館
    -0.05
    ardon
    -0.05
    POSITIVE LOGITS
    -match
    0.11
     Matches
    0.10
     Matcher
    0.10
     matches
    0.10
    Matches
    0.10
     match
    0.10
    _match
    0.10
    .matches
    0.10
    .Match
    0.10
    match
    0.09
    Activations Density 0.035%

    No Known Activations