© 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. 61885
    Prev
    Next
    INDEX
    Explanations

    details about vehicle accidents and the involved parties

    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
     Hawai
    -0.07
     Seattle
    -0.07
    Seattle
    -0.07
    arine
    -0.07
    élé
    -0.07
    ìĦł
    -0.07
     Pacific
    -0.07
     Honolulu
    -0.07
    ASSERT
    -0.07
    ãģŁãĤī
    -0.07
    POSITIVE LOGITS
    Ohio
    0.09
     Ohio
    0.08
     ohio
    0.07
     Flem
    0.07
     Niagara
    0.07
    avo
    0.07
     Pennsylvania
    0.06
     Toledo
    0.06
    âĢ
    0.06
    ниÑĤ
    0.06
    Activations Density 0.008%

    No Known Activations