© 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. 63111
    Prev
    Next
    INDEX
    Explanations

    references to isolation and loneliness

    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
    eum
    -0.07
    lite
    -0.07
    lio
    -0.06
    ulum
    -0.06
    áŁĴáŀ
    -0.06
    GY
    -0.06
    ls
    -0.06
    ron
    -0.06
    ollapse
    -0.06
    jing
    -0.06
    POSITIVE LOGITS
     baÅŁÄ±na
    0.09
    isol
    0.08
    /single
    0.07
    .nih
    0.07
    çĭ¼
    0.07
    èŃľ
    0.07
     solitary
    0.07
     à¹Ĩ
    0.07
    857
    0.07
     lonely
    0.07
    Activations Density 0.016%

    No Known Activations