© 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. 39077
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and standards in various 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
    egal
    -0.08
    аÑģ
    -0.07
    otos
    -0.07
    imler
    -0.07
    oupon
    -0.07
    าย
    -0.07
    lesia
    -0.07
    enco
    -0.07
    owa
    -0.07
    owo
    -0.07
    POSITIVE LOGITS
    enek
    0.08
    ürnberg
    0.08
    anan
    0.08
     orth
    0.08
    omencl
    0.07
    atively
    0.07
    atives
    0.07
    RG
    0.07
    ollen
    0.07
    erus
    0.07
    Activations Density 0.158%

    No Known Activations