© 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. 9-LLAMASCOPE-RES-131K
    11. 94057
    Prev
    Next
    INDEX
    Explanations

    terms related to stasis or lack of progress

    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
    ssi
    -0.07
    IMS
    -0.07
    aat
    -0.07
     bell
    -0.07
    enton
    -0.06
    bell
    -0.06
    λον
    -0.06
    ÄĽti
    -0.06
    eft
    -0.06
    nika
    -0.06
    POSITIVE LOGITS
    punkt
    0.07
    )((((
    0.07
    ospel
    0.07
    _CUDA
    0.07
    Ñīи
    0.07
     McKenzie
    0.06
    ué
    0.06
    etail
    0.06
    ishment
    0.06
    usra
    0.06
    Activations Density 0.016%

    No Known Activations