© 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. 124473
    Prev
    Next
    INDEX
    Explanations

    terms related to dyslexia and its association with individuals

    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
    avy
    -0.07
    703
    -0.07
    igo
    -0.07
    ERRU
    -0.07
    ç±į
    -0.06
    olina
    -0.06
    Nonnull
    -0.06
    izi
    -0.06
    zioni
    -0.06
    оÑģÑĮ
    -0.06
    POSITIVE LOGITS
    sville
    0.07
    meric
    0.07
    erman
    0.07
    esser
    0.06
    posium
    0.06
     dys
    0.06
    .poster
    0.06
     unint
    0.06
    /dis
    0.06
     Kling
    0.06
    Activations Density 0.004%

    No Known Activations