© 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. 61017
    Prev
    Next
    INDEX
    Explanations

    mentions of car brands and automotive terminology

    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
    arda
    -0.06
    ww
    -0.06
    grade
    -0.06
     working
    -0.06
     cap
    -0.06
    cko
    -0.05
     Jah
    -0.05
    缼
    -0.05
    ypress
    -0.05
     entry
    -0.05
    POSITIVE LOGITS
    idlo
    0.08
    ufe
    0.07
    bstract
    0.07
    éf
    0.07
    pq
    0.07
    645
    0.07
    -valu
    0.07
    ussy
    0.07
    leftright
    0.07
     dealership
    0.07
    Activations Density 0.006%

    No Known Activations