© 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. 27100
    Prev
    Next
    INDEX
    Explanations

    details related to community safety measures and support systems

    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
     styles
    -0.07
    Æ°á»Ŀi
    -0.06
    udies
    -0.06
    ноÑģи
    -0.06
     Styles
    -0.06
     genu
    -0.06
    iosity
    -0.06
    usters
    -0.06
    _styles
    -0.06
    erm
    -0.06
    POSITIVE LOGITS
     activation
    0.08
     activations
    0.08
     sẵn
    0.07
    activation
    0.07
     ready
    0.07
    esini
    0.07
     Activation
    0.07
     inventor
    0.07
    ready
    0.07
    ulo
    0.07
    Activations Density 0.007%

    No Known Activations