© 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. 96141
    Prev
    Next
    INDEX
    Explanations

    assertions and discussions about systemic issues in society, especially regarding health, social justice, and environmental concerns

    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
    _graphics
    -0.07
    ãĤ¿ãĥ«
    -0.07
    ÑģÑıÑĤ
    -0.07
    سر
    -0.07
     (*((
    -0.06
     rekl
    -0.06
    esp
    -0.06
    à¸ļาย
    -0.06
     kostenlose
    -0.06
    ÑģÑı
    -0.06
    POSITIVE LOGITS
    zes
    0.07
    REA
    0.06
     ours
    0.06
     bulls
    0.06
    bull
    0.06
    auge
    0.06
    Caller
    0.06
    umba
    0.06
     summons
    0.06
    450
    0.06
    Activations Density 0.028%

    No Known Activations