© 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. 17722
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and rulings

    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
     Braun
    -0.07
    aggi
    -0.07
    _planes
    -0.07
    ÙĤÙĦ
    -0.07
    æį®
    -0.07
    ÙĪÙģ
    -0.06
    زاÙĨ
    -0.06
    оÑĢÑĤ
    -0.06
    .newBuilder
    -0.06
    .getDocument
    -0.06
    POSITIVE LOGITS
    alth
    0.07
    block
    0.06
    rama
    0.06
    rane
    0.06
     Hut
    0.06
     ect
    0.06
    ãĥ¼ãĥ
    0.06
     continues
    0.06
     continue
    0.06
     proceed
    0.06
    Activations Density 0.039%

    No Known Activations