© 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. 123782
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases and regulations

    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
    rix
    -0.07
    alle
    -0.07
     Haupt
    -0.07
     Schiff
    -0.06
    inand
    -0.06
    ÑĢап
    -0.06
    ensen
    -0.06
    mans
    -0.06
    icast
    -0.06
    anlar
    -0.06
    POSITIVE LOGITS
     about
    0.08
     that
    0.08
     which
    0.07
     concerning
    0.07
     Sok
    0.07
     regarding
    0.06
     earlier
    0.06
    æľīåħ³
    0.06
    dds
    0.06
     med
    0.06
    Activations Density 0.034%

    No Known Activations