© 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. 95534
    Prev
    Next
    INDEX
    Explanations

    emotional or impactful moments related to personal growth

    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
     titular
    -0.07
    erna
    -0.06
    å®Ŀ
    -0.06
     رÙĪÙħ
    -0.06
    awai
    -0.06
    oyer
    -0.06
    Pixmap
    -0.06
     false
    -0.06
    acente
    -0.06
     kart
    -0.06
    POSITIVE LOGITS
    endor
    0.07
    ç«ĭãģ¡
    0.07
    kil
    0.07
    wick
    0.07
     Wich
    0.07
    -feedback
    0.06
    _likelihood
    0.06
    iesta
    0.06
    verbatim
    0.06
     kennenlernen
    0.06
    Activations Density 0.000%

    No Known Activations