© 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. 121394
    Prev
    Next
    INDEX
    Explanations

    references to organizational structures and governance

    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
    /her
    -0.08
    iceps
    -0.07
    ÅĽli
    -0.07
    eled
    -0.06
    инг
    -0.06
    ctl
    -0.06
     Vernon
    -0.06
    antro
    -0.06
    porto
    -0.06
    она
    -0.06
    POSITIVE LOGITS
    оÑĢони
    0.07
    _hub
    0.06
    pery
    0.06
    izada
    0.06
    uel
    0.06
    rides
    0.06
    ora
    0.06
    Ø´Ùħ
    0.06
    izado
    0.06
    notated
    0.06
    Activations Density 0.065%

    No Known Activations