© 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. 15154
    Prev
    Next
    INDEX
    Explanations

    references to regulations and their implications on various sectors

    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
    ?type
    -0.07
    onto
    -0.07
    angi
    -0.07
    ussen
    -0.07
     earlier
    -0.07
    ?q
    -0.07
    INTR
    -0.06
     later
    -0.06
     previously
    -0.06
    æĸ¹éĿ¢
    -0.06
    POSITIVE LOGITS
    /current
    0.10
    ,current
    0.08
     Current
    0.08
     CURRENT
    0.07
     current
    0.07
     situation
    0.07
    ugins
    0.07
     incarnation
    0.07
    sit
    0.07
    -current
    0.07
    Activations Density 0.054%

    No Known Activations