© 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 EvalsExportsAPI 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. 126516
    Prev
    Next
    INDEX
    Explanations

    content related to regulations and restrictions, particularly regarding photography and copyright

    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
     <+
    -0.07
     Weak
    -0.06
    weak
    -0.06
    ought
    -0.06
     ä¿®
    -0.06
     weak
    -0.06
    ohn
    -0.06
     rub
    -0.06
    olle
    -0.06
    well
    -0.06
    POSITIVE LOGITS
     our
    0.12
     ourselves
    0.10
     ours
    0.09
    æĪij们çļĦ
    0.09
     kami
    0.08
     nuestro
    0.08
     nosso
    0.08
     we
    0.08
    ibal
    0.08
    æĪijåĢij
    0.08
    Activations Density 0.028%

    No Known Activations