© 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. 29206
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal contexts related to vehicular accidents

    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
    abay
    -0.08
    steller
    -0.07
    ikipedia
    -0.07
    opsis
    -0.07
    unami
    -0.07
    CCR
    -0.07
    úsqueda
    -0.07
    frag
    -0.07
    odash
    -0.07
    pitch
    -0.07
    POSITIVE LOGITS
    :///
    0.06
     Uncategorized
    0.06
    -tank
    0.06
     McM
    0.05
    .mozilla
    0.05
    ypes
    0.05
    anje
    0.05
     sen
    0.05
    etro
    0.05
     Rolling
    0.05
    Activations Density 0.001%

    No Known Activations