© 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. 79788
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events

    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
    588
    -0.07
    PIO
    -0.07
     Belg
    -0.06
    ad
    -0.06
    aran
    -0.06
    277
    -0.06
    Ĥ¨
    -0.06
     Napoleon
    -0.06
    QA
    -0.06
    gone
    -0.05
    POSITIVE LOGITS
    emen
    0.08
    chet
    0.07
    .asm
    0.07
     Duy
    0.07
    oby
    0.06
    .yahoo
    0.06
    à¸Ħรà¸ļ
    0.06
    subst
    0.06
    .www
    0.06
    idge
    0.06
    Activations Density 0.009%

    No Known Activations