© 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. 53867
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to web development and scripting

    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
    endir
    -0.07
     Roth
    -0.06
    loh
    -0.06
    LETE
    -0.06
    riad
    -0.06
    μί
    -0.06
    ç¾½
    -0.06
    loit
    -0.06
    sey
    -0.06
    ihil
    -0.06
    POSITIVE LOGITS
     tá»Ń
    0.06
    ché
    0.06
     Petite
    0.06
    ouri
    0.06
    uide
    0.06
     Karlov
    0.06
    asta
    0.06
     fakat
    0.06
    eniable
    0.06
    apa
    0.06
    Activations Density 0.004%

    No Known Activations