© 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. 94058
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights violations and governmental actions

    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
    ULE
    -0.07
    ules
    -0.07
    annonce
    -0.07
    lington
    -0.07
    ÙĨب
    -0.07
    amework
    -0.07
    หว
    -0.07
    AREST
    -0.06
    linky
    -0.06
    ='".$_
    -0.06
    POSITIVE LOGITS
     gall
    0.07
    ilers
    0.06
     dip
    0.06
     fine
    0.06
    olare
    0.06
     NaN
    0.05
     Boeh
    0.05
     dipped
    0.05
    amped
    0.05
     truth
    0.05
    Activations Density 0.038%

    No Known Activations