© 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. 70577
    Prev
    Next
    INDEX
    Explanations

    references to the term "Guangzhou" and other related geographical and scientific terminology

    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
    priv
    -0.07
    endor
    -0.07
    ietf
    -0.07
    ocos
    -0.07
    ocols
    -0.07
    anova
    -0.07
    ôle
    -0.07
    č↵č↵č↵č↵
    -0.07
    ALCHEMY
    -0.07
    cake
    -0.06
    POSITIVE LOGITS
    acho
    0.06
    fik
    0.06
    matic
    0.06
    criptor
    0.06
    gg
    0.06
    uates
    0.06
    nam
    0.06
    ouston
    0.06
    fic
    0.06
    ning
    0.06
    Activations Density 0.010%

    No Known Activations