© 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. 14284
    Prev
    Next
    INDEX
    Explanations

    references to social media sharing options and functionality

    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
    -0.06
    527
    -0.06
     spin
    -0.06
    andom
    -0.06
     Patton
    -0.06
     (
    -0.06
     freshman
    -0.05
    âĢ¦
    -0.05
     history
    -0.05
    ↵
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĥĸ
    0.09
    ERO
    0.08
    .Framework
    0.08
    Tweet
    0.07
    ãĥĥãĥĦ
    0.07
    -article
    0.07
    ovu
    0.07
    achat
    0.07
    .social
    0.07
    .Unicode
    0.07
    Activations Density 0.004%

    No Known Activations