© 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. 69435
    Prev
    Next
    INDEX
    Explanations

    different forms of the word "choose" 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
    ìĩ
    -0.06
     Gh
    -0.06
    bre
    -0.06
    ̧
    -0.06
     naturally
    -0.05
    organ
    -0.05
     mus
    -0.05
    ã
    -0.05
    одо
    -0.05
     colony
    -0.05
    POSITIVE LOGITS
    (choices
    0.07
    OrCreate
    0.07
    IRR
    0.07
    erras
    0.07
    529
    0.06
     chooses
    0.06
    еÑĨÑĤ
    0.06
     nit
    0.06
    imps
    0.06
    yy
    0.06
    Activations Density 0.001%

    No Known Activations