© 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. 123332
    Prev
    Next
    INDEX
    Explanations

    references to residents or population 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
    ogan
    -0.06
    ernet
    -0.06
    arton
    -0.06
    ji
    -0.06
    uyu
    -0.06
    INESS
    -0.06
    iglia
    -0.06
    less
    -0.06
     Ged
    -0.06
    彩票
    -0.06
    POSITIVE LOGITS
    ariant
    0.07
    hausen
    0.07
    soever
    0.07
     Schultz
    0.06
    intendent
    0.06
     Cousins
    0.06
    íĭ
    0.06
    ozy
    0.06
    ymoon
    0.06
    ceeded
    0.06
    Activations Density 0.000%

    No Known Activations