© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 103901
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword 'use', particularly in a programming context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ÑĢави
    -0.08
    à¹Īาย
    -0.08
    aar
    -0.08
     inval
    -0.07
    ÑĢÑĸм
    -0.07
    лаÑģ
    -0.06
    asaki
    -0.06
     helf
    -0.06
    ruptions
    -0.06
    ëį°
    -0.06
    POSITIVE LOGITS
    apons
    0.06
    otes
    0.06
    apon
    0.06
    uble
    0.06
    asn
    0.06
    allel
    0.06
    amba
    0.05
    adero
    0.05
    ceph
    0.05
    дап
    0.05
    Activations Density 0.000%

    No Known Activations