© 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. 27828
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its variations

    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
    ingly
    -0.07
    el
    -0.06
    swift
    -0.06
     consistently
    -0.06
    ed
    -0.06
    ãĥ¼ãĥĭ
    -0.05
     Gonz
    -0.05
     bab
    -0.05
     Tre
    -0.05
    Ù
    -0.05
    POSITIVE LOGITS
     اÙĦÙħتØŃدة
    0.09
    bai
    0.08
     addCriterion
    0.07
    /misc
    0.07
    ç·Ĵ
    0.07
    rouch
    0.07
    lÃŃÄį
    0.07
    anoia
    0.07
    éĻ¢
    0.07
    -addons
    0.07
    Activations Density 0.005%

    No Known Activations