© 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. 53731
    Prev
    Next
    INDEX
    Explanations

    uses of the word "proper" and its variants in different 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
    olor
    -0.07
    arine
    -0.07
    vod
    -0.07
    alog
    -0.06
    acters
    -0.06
    ary
    -0.06
    elic
    -0.06
    IX
    -0.06
    AZY
    -0.06
    ãĥŃãĥ¼
    -0.06
    POSITIVE LOGITS
    fully
    0.13
    ment
    0.09
    erif
    0.08
    amate
    0.08
    bred
    0.08
    mente
    0.08
     functioning
    0.08
    -function
    0.07
    Subset
    0.07
    quisa
    0.07
    Activations Density 0.008%

    No Known Activations