© 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. 16871
    Prev
    Next
    INDEX
    Explanations

    words related to redoing or restoring actions

    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
    eÅŁ
    -0.07
    156
    -0.07
    cakes
    -0.06
    halt
    -0.06
    //{{
    -0.06
    eri
    -0.06
     Klein
    -0.06
    eum
    -0.06
    lÃŃÄį
    -0.06
    qli
    -0.06
    POSITIVE LOGITS
     stru
    0.07
    ("(%
    0.07
    IGHL
    0.06
     proportion
    0.06
    fea
    0.06
    ater
    0.06
     re
    0.06
    nyder
    0.06
    tribution
    0.06
    ssi
    0.06
    Activations Density 0.027%

    No Known Activations