© 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. 85477
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and governmental figures

    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
    ãĥĩãĤ£ãĤ¢
    -0.06
     growth
    -0.06
     flux
    -0.06
    IDDEN
    -0.06
     Luk
    -0.05
     Clause
    -0.05
     Flux
    -0.05
     reb
    -0.05
     rol
    -0.05
     Rh
    -0.05
    POSITIVE LOGITS
    eker
    0.07
    itionally
    0.07
    ucha
    0.07
    odu
    0.07
    dni
    0.07
    gii
    0.07
    Release
    0.07
    ÑĤого
    0.07
    allet
    0.06
     Crime
    0.06
    Activations Density 0.002%

    No Known Activations