© 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. 5737
    Prev
    Next
    INDEX
    Explanations

    spatial arrangements or settings in narratives

    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
    odem
    -0.07
    _literals
    -0.06
    лÑİб
    -0.06
    ngle
    -0.06
     dra
    -0.06
    serter
    -0.06
    apg
    -0.06
    lucent
    -0.06
    .createFrom
    -0.06
    ture
    -0.05
    POSITIVE LOGITS
    ullo
    0.07
    UPLE
    0.07
    æµİ
    0.07
     nÄĽjaké
    0.06
    reamble
    0.06
    street
    0.06
     Tomas
    0.06
    auc
    0.06
    isch
    0.06
    /tos
    0.06
    Activations Density 0.022%

    No Known Activations