© 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. 54187
    Prev
    Next
    INDEX
    Explanations

    instances of the word "become" and its variations, indicating changes and transformations

    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
    á»ĵn
    -0.07
    athi
    -0.07
    oppable
    -0.07
    /UIKit
    -0.06
    icture
    -0.06
    QRSTUV
    -0.06
    rene
    -0.06
    izik
    -0.06
    ÚĨ
    -0.06
    ebek
    -0.06
    POSITIVE LOGITS
    cn
    0.07
    utow
    0.06
     lo
    0.06
    oons
    0.06
    ley
    0.06
    dde
    0.06
    ende
    0.05
    ków
    0.05
    embr
    0.05
    owo
    0.05
    Activations Density 0.022%

    No Known Activations