© 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. 69262
    Prev
    Next
    INDEX
    Explanations

    references to user interfaces

    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
     Machine
    -0.07
    -Owned
    -0.07
    Ãłnh
    -0.07
     machine
    -0.07
    falls
    -0.07
    beck
    -0.07
    _KEYWORD
    -0.07
    /tiny
    -0.06
    fall
    -0.06
     TestUtils
    -0.06
    POSITIVE LOGITS
     interface
    0.08
    interface
    0.07
    roud
    0.07
    oup
    0.07
    Interface
    0.06
    /interface
    0.06
    -interface
    0.06
    rove
    0.06
     freak
    0.06
    elman
    0.06
    Activations Density 0.021%

    No Known Activations