© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17738
    Prev
    Next
    INDEX
    Explanations

    the title of a specific comic anthology

    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
    enso
    -0.07
    enses
    -0.07
    avax
    -0.06
    anki
    -0.06
     Cassidy
    -0.06
     MSE
    -0.06
     bean
    -0.06
    itemap
    -0.06
    entarios
    -0.06
    perty
    -0.06
    POSITIVE LOGITS
     дело
    0.07
    ValueCollection
    0.06
    èĪª
    0.06
    FFFFFFFF
    0.06
    andez
    0.06
    нод
    0.06
    elib
    0.06
    inez
    0.06
    161
    0.06
    BackPressed
    0.06
    Activations Density 0.000%

    No Known Activations