© 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. 63108
    Prev
    Next
    INDEX
    Explanations

    instances of societal conflict and crowd dynamics

    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
    URAL
    -0.07
    otta
    -0.06
     Bomb
    -0.06
    访
    -0.06
     buz
    -0.06
    cook
    -0.06
    leck
    -0.06
     jealous
    -0.06
     gunmen
    -0.06
     Caf
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    /tos
    0.06
    aml
    0.06
    alc
    0.06
    FirstChild
    0.06
     æ½
    0.06
    ValuePair
    0.06
     Goddess
    0.06
    @nate
    0.06
    bootstrap
    0.06
    Activations Density 0.010%

    No Known Activations