© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128332
    Prev
    Next
    INDEX
    Explanations

    expressions of requests for assistance or advice

    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
    -urlencoded
    -0.08
     would
    -0.07
     stim
    -0.06
     wouldn
    -0.06
    -avatar
    -0.06
    eken
    -0.06
    alk
    -0.06
    ponder
    -0.06
    Would
    -0.06
     ded
    -0.06
    POSITIVE LOGITS
    ITTE
    0.07
    amework
    0.07
    iah
    0.07
    elp
    0.07
    AIM
    0.07
     yardımcı
    0.06
    igg
    0.06
     aid
    0.06
    ubo
    0.06
     ì¦ī
    0.06
    Activations Density 0.001%

    No Known Activations