© 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. 91585
    Prev
    Next
    INDEX
    Explanations

    references to numbers and quantities

    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
    ÃĹ↵↵
    -0.07
    åŃ£
    -0.06
     Stef
    -0.06
    ponents
    -0.06
    quit
    -0.05
    stanov
    -0.05
    _slices
    -0.05
     CAD
    -0.05
     Mull
    -0.05
     Ost
    -0.05
    POSITIVE LOGITS
    овоÑĢ
    0.07
    forman
    0.07
    ktop
    0.07
    otch
    0.07
    deniz
    0.07
     Harden
    0.07
     questions
    0.07
    _ATTRIB
    0.07
    eldorf
    0.07
     lessons
    0.07
    Activations Density 0.024%

    No Known Activations