© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62824
    Prev
    Next
    INDEX
    Explanations

    statements and phrases related to political commentary and opinions

    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
    -<?
    -0.08
    èĥ½å¤Ł
    -0.07
    Å¡ak
    -0.07
    bohydr
    -0.07
    ↵↵
    -0.07
     parc
    -0.07
    otten
    -0.07
     <%=
    -0.07
    ¥IJ
    -0.06
     activeClassName
    -0.06
    POSITIVE LOGITS
     &
    0.12
     probs
    0.09
     lots
    0.08
     @
    0.08
    ÌĢ
    0.08
    jee
    0.07
    amp
    0.07
     #
    0.07
     &,
    0.07
    -&
    0.07
    Activations Density 0.002%

    No Known Activations