© 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. 16532
    Prev
    Next
    INDEX
    Explanations

    terms related to restrictions and prohibitions

    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
    uiltin
    -0.07
    ustin
    -0.07
    عاÙĨ
    -0.07
    ÙģÙĩ
    -0.07
    á»ijt
    -0.06
    داÙĨ
    -0.06
    apy
    -0.06
    othy
    -0.06
    ENABLE
    -0.06
    onga
    -0.06
    POSITIVE LOGITS
     future
    0.09
    future
    0.08
     ever
    0.07
     forever
    0.07
     anywhere
    0.07
     Future
    0.07
     participation
    0.07
    uture
    0.07
    epad
    0.07
     access
    0.06
    Activations Density 0.008%

    No Known Activations