© 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. 31742
    Prev
    Next
    INDEX
    Explanations

    references to single or unmarried individuals and their experiences

    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
    .connections
    -0.08
    ozem
    -0.07
    èn
    -0.07
    undan
    -0.07
    jang
    -0.07
    _lite
    -0.07
    indow
    -0.07
    ircular
    -0.07
    amber
    -0.06
     Guzzle
    -0.06
    POSITIVE LOGITS
    /single
    0.10
    tons
    0.07
     single
    0.07
     status
    0.07
    (single
    0.07
    -single
    0.07
    357
    0.07
    .single
    0.07
    ucci
    0.07
     lonely
    0.06
    Activations Density 0.007%

    No Known Activations