© 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. 121497
    Prev
    Next
    INDEX
    Explanations

    terms and structures related to mathematical theorems and equations

    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
    ilan
    -0.08
     meteor
    -0.07
    meteor
    -0.07
     Meteor
    -0.06
     brains
    -0.06
    edBy
    -0.06
    brains
    -0.06
    blo
    -0.06
    ÑħÑĥ
    -0.06
     kit
    -0.06
    POSITIVE LOGITS
    veis
    0.07
     Bölüm
    0.07
    \Id
    0.07
    .stringify
    0.07
    umped
    0.07
    ç¼ĸåı·
    0.07
    offsetof
    0.06
     numbering
    0.06
     номеÑĢ
    0.06
    ahoma
    0.06
    Activations Density 0.005%

    No Known Activations