© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18298
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and related demonstrative terms

    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
     Hughes
    -0.07
    amac
    -0.07
    DisplayStyle
    -0.07
     Hermes
    -0.06
    plat
    -0.06
    contra
    -0.06
    _PCM
    -0.06
     contra
    -0.06
     Contrast
    -0.06
     contracting
    -0.06
    POSITIVE LOGITS
    że
    0.07
    ucci
    0.07
    atak
    0.07
    ulate
    0.07
    _gb
    0.07
    ä¸ĺ
    0.06
     latter
    0.06
     Ñģб
    0.06
    ichni
    0.06
    ÏģιÏĥÏĦ
    0.06
    Activations Density 0.033%

    No Known Activations