© 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. 5-LLAMASCOPE-RES-131K
    11. 126811
    Prev
    Next
    INDEX
    Explanations

    prominent literary figures or authors

    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
     planta
    -0.07
    585
    -0.07
    owan
    -0.06
    QualifiedName
    -0.06
     Fleming
    -0.06
    uji
    -0.06
    enberg
    -0.06
    bury
    -0.06
    apo
    -0.06
    ãģ¨æĢĿ
    -0.06
    POSITIVE LOGITS
    uni
    0.07
     ëĦ¤ìĿ´íĬ¸
    0.07
    setProperty
    0.06
     Bast
    0.06
    RIA
    0.06
    atively
    0.06
    .native
    0.06
    oppers
    0.06
    -UA
    0.06
    DRV
    0.06
    Activations Density 0.001%

    No Known Activations