© 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. 15-LLAMASCOPE-RES-131K
    11. 87228
    Prev
    Next
    INDEX
    Explanations

    phrases indicating roles or titles from individuals, particularly in leadership positions

    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
    ald
    -0.08
    ury
    -0.07
    agra
    -0.07
    lep
    -0.06
    anim
    -0.06
     laut
    -0.06
    MethodImpl
    -0.06
    Ãłu
    -0.06
     Lever
    -0.06
     Caval
    -0.06
    POSITIVE LOGITS
     lead
    0.07
     founder
    0.06
     Founder
    0.06
    inear
    0.06
    à¸ĺ
    0.06
    quals
    0.06
    strate
    0.06
    łĢ
    0.06
     inde
    0.06
    adden
    0.06
    Activations Density 0.012%

    No Known Activations