© 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. 38460
    Prev
    Next
    INDEX
    Explanations

    references to friendship and relationships

    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
    izon
    -0.08
    izona
    -0.07
    .uml
    -0.07
    trap
    -0.06
     antlr
    -0.06
    hea
    -0.06
    ppy
    -0.06
    idian
    -0.06
    uby
    -0.06
    ernel
    -0.06
    POSITIVE LOGITS
     childhood
    0.07
    Abort
    0.06
    414
    0.06
     shared
    0.06
    å§ī
    0.06
    YW
    0.06
     marg
    0.06
    shared
    0.06
     laut
    0.06
     sharing
    0.06
    Activations Density 0.031%

    No Known Activations