© 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. 72996
    Prev
    Next
    INDEX
    Explanations

    elements related to legal proceedings

    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
    .Automation
    -0.08
    åĢī
    -0.08
    .Invariant
    -0.07
    ÄIJT
    -0.07
    reso
    -0.07
    à¹ģà¸ŀร
    -0.07
    otts
    -0.07
    Reusable
    -0.07
    lesia
    -0.07
    kees
    -0.07
    POSITIVE LOGITS
    bench
    0.06
    emic
    0.06
     diam
    0.06
     framework
    0.06
     pneum
    0.06
     after
    0.05
     interven
    0.05
    за
    0.05
     skeleton
    0.05
     final
    0.05
    Activations Density 0.013%

    No Known Activations