© 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. 94162
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to drowning and related incidents

    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
    upertino
    -0.08
    oint
    -0.07
    roma
    -0.07
    ERCHANT
    -0.07
    ial
    -0.07
     sayıda
    -0.06
    ocoa
    -0.06
    eu
    -0.06
    teen
    -0.06
    eur
    -0.06
    POSITIVE LOGITS
    ouser
    0.07
    edin
    0.07
    plain
    0.07
    γοÏħ
    0.07
    icone
    0.07
    ushima
    0.07
     in
    0.06
     plain
    0.06
    vertise
    0.06
    hound
    0.06
    Activations Density 0.003%

    No Known Activations