© 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. 80792
    Prev
    Next
    INDEX
    Explanations

    words related to specialized applications or functions

    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
    iedo
    -0.07
    itz
    -0.07
    reib
    -0.07
    ÄĻk
    -0.07
    _UNIX
    -0.07
    _AG
    -0.06
    rix
    -0.06
    raction
    -0.06
     Editors
    -0.06
     Briggs
    -0.06
    POSITIVE LOGITS
    pname
    0.07
    ritel
    0.07
    tight
    0.06
     Wol
    0.06
    OTA
    0.06
    ecimal
    0.06
    dre
    0.05
    ota
    0.05
    emente
    0.05
    ANDLE
    0.05
    Activations Density 0.001%

    No Known Activations