© 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. 14143
    Prev
    Next
    INDEX
    Explanations

    references to various web technologies and coding languages, particularly HTML and CSS

    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
    宿
    -0.07
    ré
    -0.06
     Tate
    -0.06
     Cook
    -0.06
     Blank
    -0.06
    ssf
    -0.06
    ort
    -0.05
     pau
    -0.05
    ressing
    -0.05
    -margin
    -0.05
    POSITIVE LOGITS
    IZES
    0.07
    ully
    0.07
    DivElement
    0.07
    /opt
    0.07
    icz
    0.07
    mia
    0.07
    IPS
    0.07
    ohen
    0.07
    ietet
    0.07
    esar
    0.07
    Activations Density 0.022%

    No Known Activations