© 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. 85762
    Prev
    Next
    INDEX
    Explanations

    references to beta-related substances or activities

    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
    è¿Ļä¸Ģ
    -0.07
     THIS
    -0.06
    Ngh
    -0.06
     Foley
    -0.06
     Hardy
    -0.06
    usch
    -0.06
    ć
    -0.06
    irst
    -0.06
     ald
    -0.06
     THESE
    -0.06
    POSITIVE LOGITS
    chts
    0.07
    ocks
    0.07
    averse
    0.07
     Caucus
    0.06
    /Foundation
    0.06
    asper
    0.06
    lique
    0.06
    ayout
    0.06
    estate
    0.06
    atra
    0.06
    Activations Density 0.000%

    No Known Activations