© 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. 116471
    Prev
    Next
    INDEX
    Explanations

    terms related to content management and user experience features

    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
    formats
    -0.06
    .idea
    -0.06
    ÑĪÑĥ
    -0.06
     Äijẳng
    -0.06
    éªĮ
    -0.06
    isay
    -0.06
    .MouseDown
    -0.06
    anvas
    -0.06
    uplic
    -0.06
    ç¾
    -0.06
    POSITIVE LOGITS
     parental
    0.08
     children
    0.07
     parent
    0.07
    childs
    0.07
     Safety
    0.07
    otos
    0.06
     Limits
    0.06
     ØŃساب
    0.06
     settings
    0.06
     Children
    0.06
    Activations Density 0.003%

    No Known Activations