© 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. 74132
    Prev
    Next
    INDEX
    Explanations

    legal terms and definitions related to liability and legal processes

    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
    å¢
    -0.06
    pton
    -0.05
    2
    -0.05
    orraine
    -0.05
    ASI
    -0.05
    Desk
    -0.05
     resid
    -0.05
    ancia
    -0.05
    obre
    -0.05
     $
    -0.05
    POSITIVE LOGITS
    ëŀĢ
    0.08
    /Runtime
    0.07
    /of
    0.07
     داشتÙĨ
    0.07
    TEX
    0.07
    CommandEvent
    0.07
    ãģ¨ãģ¯
    0.07
     suce
    0.07
    Ñĩие
    0.07
    .ss
    0.07
    Activations Density 0.011%

    No Known Activations