© 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. 9-LLAMASCOPE-RES-131K
    11. 95820
    Prev
    Next
    INDEX
    Explanations

    inquiries and expressions of uncertainty

    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
    adb
    -0.06
    ade
    -0.06
    anel
    -0.06
    inders
    -0.06
     gra
    -0.06
    ÎĪ
    -0.06
    scape
    -0.06
    éis
    -0.06
    éĹª
    -0.06
     Moments
    -0.06
    POSITIVE LOGITS
    igon
    0.07
    acad
    0.06
    etta
    0.06
     bì
    0.06
     congreg
    0.06
     Busty
    0.06
     INCIDENTAL
    0.06
    exels
    0.06
    quam
    0.06
    anj
    0.06
    Activations Density 0.116%

    No Known Activations