© 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. 38378
    Prev
    Next
    INDEX
    Explanations

    references to moral principles and ethical considerations

    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
    .unknown
    -0.08
    andal
    -0.07
    //{{
    -0.07
    ợ
    -0.07
    repid
    -0.07
    @js
    -0.07
    swer
    -0.07
    _________________↵↵
    -0.06
    οκ
    -0.06
    \Module
    -0.06
    POSITIVE LOGITS
    mith
    0.07
    pending
    0.07
    jak
    0.07
    rs
    0.07
     ability
    0.06
    δη
    0.06
    axter
    0.06
    ione
    0.06
     tou
    0.06
    asaki
    0.06
    Activations Density 0.001%

    No Known Activations