© 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. 116711
    Prev
    Next
    INDEX
    Explanations

    the name "Diane" and its variations in different contexts

    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
    اÙĨÙĩ
    -0.07
    onald
    -0.07
    TINGS
    -0.07
    avit
    -0.07
    aal
    -0.07
    tings
    -0.07
    ald
    -0.07
    дав
    -0.06
    acey
    -0.06
    äd
    -0.06
    POSITIVE LOGITS
    ched
    0.07
    anton
    0.07
    kees
    0.06
    zelf
    0.06
    209
    0.06
    etch
    0.06
    оген
    0.06
    lou
    0.06
     siz
    0.06
    omu
    0.06
    Activations Density 0.003%

    No Known Activations