© 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. 27621
    Prev
    Next
    INDEX
    Explanations

    vocabulary associated with complexity and depth in tasks and subjects

    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
    AEA
    -0.07
    ãĤĩ
    -0.07
    []={
    -0.06
    allen
    -0.06
    velt
    -0.06
    elsea
    -0.06
    utar
    -0.06
    ÅĻet
    -0.06
    thur
    -0.06
    azel
    -0.06
    POSITIVE LOGITS
     possible
    0.14
     imaginable
    0.14
     posible
    0.12
     ever
    0.12
    possible
    0.12
     Possible
    0.11
     ÙħÙħÚ©ÙĨ
    0.11
     possÃŃvel
    0.10
     yet
    0.10
     EVER
    0.10
    Activations Density 0.113%

    No Known Activations