© 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. 116744
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    queued
    -0.08
    éĺħ读次æķ°
    -0.08
    neh
    -0.07
    /topics
    -0.07
    //{{
    -0.07
     Democracy
    -0.07
     GENERATED
    -0.07
    AxisSize
    -0.07
    CTS
    -0.07
    lÃŃ
    -0.06
    POSITIVE LOGITS
     prom
    0.06
    0.06
    ICY
    0.06
     exped
    0.06
    ency
    0.06
     strip
    0.06
    à¹Ģห
    0.06
     split
    0.05
     correspond
    0.05
    ινε
    0.05
    Activations Density 0.035%

    No Known Activations