© 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. 80803
    Prev
    Next
    INDEX
    Explanations

    HTML form elements and their attributes related to text input and text areas

    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
    esel
    -0.07
    sett
    -0.07
    skip
    -0.07
    ahl
    -0.07
     Skip
    -0.07
    Forward
    -0.06
    rient
    -0.06
     Forward
    -0.06
     pop
    -0.06
    aka
    -0.06
    POSITIVE LOGITS
    <textarea
    0.10
    textarea
    0.08
     textarea
    0.08
    .numberOfLines
    0.08
    .Multiline
    0.07
     TextArea
    0.07
    ckeditor
    0.07
    Textarea
    0.07
     multiline
    0.07
    OPEN
    0.06
    Activations Density 0.016%

    No Known Activations