© 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. 81251
    Prev
    Next
    INDEX
    Explanations

    references to regulations and legislative measures

    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
    ansen
    -0.07
    628
    -0.06
    anse
    -0.06
    792
    -0.06
     hopefully
    -0.06
    æĹĭ
    -0.06
     admittedly
    -0.06
    oren
    -0.05
     Insets
    -0.05
    424
    -0.05
    POSITIVE LOGITS
    ozem
    0.08
     خطر
    0.07
    GINE
    0.07
    ActionTypes
    0.07
    apas
    0.07
    -danger
    0.07
     çľ
    0.07
    danger
    0.07
    akan
    0.07
    ihan
    0.07
    Activations Density 0.014%

    No Known Activations