© 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. 82859
    Prev
    Next
    INDEX
    Explanations

    details related to legal terminology and concepts

    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
    ogui
    -0.07
    issen
    -0.07
    çĶ
    -0.07
    elib
    -0.07
    oday
    -0.07
    .xhtml
    -0.07
    ITER
    -0.07
     kaç
    -0.07
    uro
    -0.06
    esc
    -0.06
    POSITIVE LOGITS
     proving
    0.07
     prove
    0.06
    ìĶ
    0.06
    ayers
    0.06
     proof
    0.06
     successfully
    0.06
     based
    0.06
     Successfully
    0.06
    ÑĨÑĭ
    0.06
    based
    0.05
    Activations Density 0.003%

    No Known Activations