© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77887
    Prev
    Next
    INDEX
    Explanations

    legal and medical terminology related to negligence and duty of care

    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
    raith
    -0.08
    anou
    -0.08
    iliz
    -0.08
    nge
    -0.07
    anik
    -0.07
    reon
    -0.07
    aname
    -0.07
    angkan
    -0.07
    itsu
    -0.07
    vailability
    -0.07
    POSITIVE LOGITS
     standard
    0.08
     reasonable
    0.07
     standards
    0.07
    standard
    0.07
     Duty
    0.07
    undle
    0.06
     duty
    0.06
     reasonably
    0.06
     Standards
    0.06
     Standard
    0.06
    Activations Density 0.010%

    No Known Activations