© 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 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. 57446
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "reading" in various contexts

    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
    qli
    -0.07
    iska
    -0.07
    usic
    -0.07
    lund
    -0.07
    utex
    -0.06
    pone
    -0.06
     Prelude
    -0.06
    isk
    -0.06
    adows
    -0.06
    439
    -0.06
    POSITIVE LOGITS
     Reading
    0.09
    Reading
    0.07
    undle
    0.07
     reading
    0.07
    ieux
    0.07
    /list
    0.06
    ableObject
    0.06
     Hour
    0.06
     Shed
    0.06
     comprehension
    0.06
    Activations Density 0.010%

    No Known Activations