© 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. 5921
    Prev
    Next
    INDEX
    Explanations

    references to social issues and community challenges

    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
     jails
    -0.07
    بÙĦ
    -0.06
    icast
    -0.06
    auce
    -0.06
    OperationException
    -0.06
     stadiums
    -0.06
    -www
    -0.06
     öden
    -0.06
    ServerError
    -0.06
     ucfirst
    -0.06
    POSITIVE LOGITS
     drugs
    0.07
     drug
    0.07
    reten
    0.06
     Territory
    0.06
     Kingdom
    0.06
    æ¥ļ
    0.06
     Elijah
    0.06
    ông
    0.06
    \Base
    0.06
    éĽij
    0.06
    Activations Density 0.014%

    No Known Activations