© 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. 99199
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "de-" in words

    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
    	Copyright
    -0.07
    solete
    -0.07
    ergic
    -0.07
    OLUMN
    -0.06
    amm
    -0.06
    ÂĿ
    -0.06
    soon
    -0.06
    .gdx
    -0.06
    eligible
    -0.06
    ald
    -0.06
    POSITIVE LOGITS
    ocode
    0.07
    noch
    0.07
     Kendall
    0.07
    Fuse
    0.07
    ãĥ¼ãĥĩ
    0.06
    MENT
    0.06
     Beau
    0.06
    .scalablytyped
    0.06
    ditor
    0.06
    MBER
    0.06
    Activations Density 0.033%

    No Known Activations