© 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. 123552
    Prev
    Next
    INDEX
    Explanations

    technical specifications and maintenance instructions related to devices or systems

    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
     catch
    -0.06
     Rip
    -0.06
    nik
    -0.06
    zi
    -0.06
    bio
    -0.06
    ̣
    -0.06
    елем
    -0.06
    島
    -0.06
     islands
    -0.06
    tool
    -0.06
    POSITIVE LOGITS
     SYMBOL
    0.07
     Kush
    0.07
    deniz
    0.07
     Poz
    0.06
     indeb
    0.06
    CRYPT
    0.06
     Bookmark
    0.06
    lom
    0.06
    èĩ´
    0.06
     Kushner
    0.06
    Activations Density 0.013%

    No Known Activations