© 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. 120375
    Prev
    Next
    INDEX
    Explanations

    instances of the word "use" and variations indicating utilization or application of something

    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
    avr
    -0.08
    ivet
    -0.07
    utos
    -0.07
     keyCode
    -0.07
    Directions
    -0.07
    culus
    -0.07
    chluss
    -0.07
     دÙģاع
    -0.07
    fib
    -0.07
    utar
    -0.06
    POSITIVE LOGITS
     or
    0.08
     any
    0.07
     nor
    0.07
     Rob
    0.06
    ķĮ
    0.06
    406
    0.06
    ä»»ä½ķ
    0.06
    assin
    0.06
     amp
    0.05
    ourd
    0.05
    Activations Density 0.003%

    No Known Activations