© 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. 42555
    Prev
    Next
    INDEX
    Explanations

    coding elements related to debugging and protocol specifications

    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
     Claw
    -0.06
    reon
    -0.06
     Billion
    -0.06
     rar
    -0.06
    055
    -0.06
     Suff
    -0.05
    xes
    -0.05
     Yo
    -0.05
     Transactions
    -0.05
    è®
    -0.05
    POSITIVE LOGITS
    åģ¥
    0.08
    ãn
    0.07
    екÑģи
    0.07
     discrimination
    0.07
    trainer
    0.07
    _listener
    0.07
     discrim
    0.07
    ساÙĨÛĮ
    0.07
    qus
    0.07
    EXP
    0.07
    Activations Density 0.046%

    No Known Activations