© 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. 9-LLAMASCOPE-RES-131K
    11. 94476
    Prev
    Next
    INDEX
    Explanations

    terms related to eye care and medical conditions affecting vision

    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
    /Branch
    -0.08
    ucker
    -0.07
    inker
    -0.07
    pector
    -0.07
    rale
    -0.06
    adx
    -0.06
    vern
    -0.06
    .Assertions
    -0.06
     branches
    -0.06
     direct
    -0.06
    POSITIVE LOGITS
    tempts
    0.08
    INTR
    0.07
    etros
    0.06
    overview
    0.06
    zt
    0.06
    unma
    0.06
    anta
    0.06
    htub
    0.06
    antic
    0.06
    REET
    0.06
    Activations Density 0.003%

    No Known Activations