© 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. 18692
    Prev
    Next
    INDEX
    Explanations

    CSS styling properties and their associated values

    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
    oola
    -0.07
    :animated
    -0.07
    WRAPPER
    -0.06
    imax
    -0.06
    abstractmethod
    -0.06
    ثر
    -0.06
    .cx
    -0.06
     Saw
    -0.06
    _FB
    -0.06
    cÃŃ
    -0.06
    POSITIVE LOGITS
    anean
    0.06
    ivery
    0.06
    ris
    0.06
     BoxFit
    0.06
    ero
    0.06
    itsu
    0.06
    694
    0.06
    uyo
    0.05
    Tab
    0.05
    aton
    0.05
    Activations Density 0.016%

    No Known Activations