© 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. 26979
    Prev
    Next
    INDEX
    Explanations

    themes related to social interaction and criticism

    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
    .scalablytyped
    -0.08
    _tip
    -0.08
    ziej
    -0.07
    meli
    -0.07
     ðŁĺī↵↵
    -0.07
    eyim
    -0.07
    оÑıн
    -0.07
    ĵĺ
    -0.07
    à¥ģह
    -0.07
    chalk
    -0.07
    POSITIVE LOGITS
     extents
    0.07
    anson
    0.06
     maybe
    0.06
    ichen
    0.06
     Maybe
    0.06
     System
    0.06
    isia
    0.05
    REN
    0.05
    Ì
    0.05
    	except
    0.05
    Activations Density 0.001%

    No Known Activations