© 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. 27145
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and inquiries regarding actions or requirements

    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
     irrelevant
    -0.06
     Dead
    -0.06
     dead
    -0.06
    831
    -0.06
    DeviceInfo
    -0.05
    ener
    -0.05
    lier
    -0.05
    Ñıж
    -0.05
     R
    -0.05
    mq
    -0.05
    POSITIVE LOGITS
     belum
    0.15
     chÆ°a
    0.14
     missing
    0.13
    å°ļ
    0.13
     hadn
    0.13
    ãģ¾ãģł
    0.13
     Haven
    0.12
    æľª
    0.12
    missing
    0.11
     lacking
    0.11
    Activations Density 0.105%

    No Known Activations