© 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. 95996
    Prev
    Next
    INDEX
    Explanations

    phrases related to police and authority figures

    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
     peÄį
    -0.09
    гл
    -0.09
     hete
    -0.08
    éŀ
    -0.08
    ÙĨب
    -0.08
    Ðĩ
    -0.08
     ÑģÑĤоÑĢонÑĥ
    -0.08
     باع
    -0.08
    åľŃ
    -0.08
     hlad
    -0.08
    POSITIVE LOGITS
    472
    0.06
    729
    0.06
     Episode
    0.06
    —that
    0.05
     or
    0.05
    âĢ¦↵
    0.05
     Quantity
    0.05
    657
    0.05
    Submitted
    0.05
    enda
    0.05
    Activations Density 0.050%

    No Known Activations