© 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. 53721
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating necessity or obligation in various contexts

    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
    yan
    -0.07
     flash
    -0.07
     Kab
    -0.06
    itler
    -0.06
    iske
    -0.06
     kab
    -0.06
    ork
    -0.06
    eer
    -0.06
     pressing
    -0.06
    íĮĮ
    -0.06
    POSITIVE LOGITS
     toujours
    0.08
    amel
    0.07
     always
    0.07
    always
    0.07
    senal
    0.07
    ESA
    0.07
    .scalablytyped
    0.07
    飯
    0.07
    AutoSize
    0.07
    ãģĵãĤĵãģ«
    0.06
    Activations Density 0.019%

    No Known Activations