© 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. 15-LLAMASCOPE-RES-131K
    11. 27476
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to criminal definitions and domestic violence

    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
     unb
    -0.08
    porto
    -0.07
    :frame
    -0.07
    auc
    -0.07
    \OptionsResolver
    -0.06
    ppard
    -0.06
    ragen
    -0.06
    undle
    -0.06
    766
    -0.06
    missive
    -0.06
    POSITIVE LOGITS
     federal
    0.09
     Federal
    0.08
    Federal
    0.08
     Congressional
    0.07
     Congress
    0.07
    Congress
    0.07
     congressional
    0.07
    odore
    0.07
     U
    0.07
     federally
    0.07
    Activations Density 0.076%

    No Known Activations