© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70465
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "public" in code

    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
    anic
    -0.07
    upa
    -0.07
    shima
    -0.07
    io
    -0.06
    ux
    -0.06
     Shack
    -0.06
     Protected
    -0.06
    ed
    -0.06
    uzzle
    -0.06
    bal
    -0.06
    POSITIVE LOGITS
     "-//
    0.09
     abstract
    0.07
    pok
    0.07
    мена
    0.07
    acomment
    0.07
    uzzi
    0.06
    atori
    0.06
    activex
    0.06
    à¹Ģสà¸Ļ
    0.06
    agnost
    0.06
    Activations Density 0.003%

    No Known Activations