© 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. 18249
    Prev
    Next
    INDEX
    Explanations

    legal references related to regulations and penalties

    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
     Chapters
    -0.07
    roller
    -0.07
    rana
    -0.06
     chapters
    -0.06
    InputBorder
    -0.06
    èĶµ
    -0.06
    oot
    -0.06
     Episode
    -0.06
     Legislation
    -0.06
    ìŀij
    -0.06
    POSITIVE LOGITS
    REATE
    0.07
     titled
    0.07
    âĢı
    0.07
     dealing
    0.07
    says
    0.06
     provision
    0.06
    itled
    0.06
     deals
    0.06
    ctor
    0.06
    ạm
    0.06
    Activations Density 0.021%

    No Known Activations