© 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. 38200
    Prev
    Next
    INDEX
    Explanations

    references to elements of societal structure and themes of vulnerability

    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
    á»Ĩ
    -0.07
     ultimo
    -0.06
    els
    -0.06
    819
    -0.06
     ally
    -0.06
     Pier
    -0.06
    нин
    -0.06
    291
    -0.06
     Pen
    -0.06
     currently
    -0.05
    POSITIVE LOGITS
    OTAL
    0.07
    autiful
    0.07
    ÑĢÑĥп
    0.07
    ανδ
    0.07
    letal
    0.07
    ä¹³
    0.07
    itone
    0.07
    samp
    0.07
    ogle
    0.07
    anship
    0.06
    Activations Density 0.002%

    No Known Activations