© 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. 81414
    Prev
    Next
    INDEX
    Explanations

    words related to legal and regulatory issues

    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
    ogeneous
    -0.12
    adecimal
    -0.12
    etheless
    -0.12
    gunakan
    -0.11
    osterone
    -0.11
    ductory
    -0.11
    обÑħодим
    -0.11
    existent
    -0.10
    linear
    -0.10
    felt
    -0.10
    POSITIVE LOGITS
    eur
    0.08
    ses
    0.07
    eing
    0.07
    ei
    0.07
    tor
    0.06
    ea
    0.06
    eam
    0.06
    eer
    0.06
    amage
    0.06
     the
    0.06
    Activations Density 0.956%

    No Known Activations