© 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. 96037
    Prev
    Next
    INDEX
    Explanations

    references to locations and associated local organizations or entities

    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
    arge
    -0.07
    -cell
    -0.06
    984
    -0.06
    vice
    -0.06
    051
    -0.06
    _LAYER
    -0.06
    aggio
    -0.06
     bip
    -0.06
    ument
    -0.06
    é£
    -0.06
    POSITIVE LOGITS
    oins
    0.07
     Segment
    0.07
     LUA
    0.07
    ATCH
    0.07
     Maui
    0.07
    .lua
    0.06
    atcher
    0.06
    ERRU
    0.06
    awaii
    0.06
     Hawai
    0.06
    Activations Density 0.012%

    No Known Activations