© 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. 15-LLAMASCOPE-RES-131K
    11. 89563
    Prev
    Next
    INDEX
    Explanations

    news article references or citations

    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
    oo
    -0.07
    uate
    -0.06
    ure
    -0.06
    uality
    -0.06
    cal
    -0.06
    nc
    -0.06
    ém
    -0.06
    oya
    -0.06
    work
    -0.06
    none
    -0.06
    POSITIVE LOGITS
    rang
    0.08
    iyim
    0.07
    altar
    0.07
    çek
    0.07
     rodin
    0.07
    diet
    0.07
    erdem
    0.07
    ttl
    0.07
    krom
    0.07
    /commons
    0.07
    Activations Density 0.000%

    No Known Activations