© 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. 103862
    Prev
    Next
    INDEX
    Explanations

    references to boarding schools and their attributes

    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
    lar
    -0.06
    ikki
    -0.06
    itet
    -0.06
    zew
    -0.06
    fsp
    -0.06
     antigen
    -0.06
    uddy
    -0.06
    enna
    -0.06
    iscrimination
    -0.05
    lab
    -0.05
    POSITIVE LOGITS
    girls
    0.08
     girls
    0.08
    boys
    0.07
     aba
    0.07
    Girls
    0.07
    imet
    0.07
     Girls
    0.07
    propri
    0.07
     boarding
    0.07
    -girl
    0.07
    Activations Density 0.002%

    No Known Activations