© 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. 89803
    Prev
    Next
    INDEX
    Explanations

    references to configuration files and delete operations

    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
    çķ
    -0.07
    avel
    -0.07
     Leban
    -0.07
    à¸ļà¸Ħ
    -0.07
    DM
    -0.06
    umin
    -0.06
    cobra
    -0.06
    ffd
    -0.06
    _LL
    -0.06
    ">//
    -0.06
    POSITIVE LOGITS
    eyse
    0.06
     åĨĨ
    0.06
    è°·
    0.06
    Framework
    0.06
    zers
    0.06
    /OR
    0.06
    APE
    0.06
    \OptionsResolver
    0.05
    asm
    0.05
     Katy
    0.05
    Activations Density 0.001%

    No Known Activations