© 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. 108770
    Prev
    Next
    INDEX
    Explanations

    concepts related to technology and software

    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
    oard
    -0.08
    ãĥĨãĥ«
    -0.07
    #__
    -0.07
    ãĤ¹ãĤ¯
    -0.07
    ezi
    -0.07
    uzey
    -0.07
    à¹Īาà¸Ļ
    -0.07
    leston
    -0.07
    _DS
    -0.06
     Burl
    -0.06
    POSITIVE LOGITS
    open
    0.08
     standards
    0.08
     compatibility
    0.08
     open
    0.08
     Open
    0.08
     univers
    0.07
    Open
    0.07
     openness
    0.07
     vendor
    0.07
     Standards
    0.07
    Activations Density 0.091%

    No Known Activations