© 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. 81954
    Prev
    Next
    INDEX
    Explanations

    sentences expressing individual opinions or personal reflections

    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
     Advice
    -0.07
    à¸ļà¸Ĺ
    -0.07
    earn
    -0.07
     Hint
    -0.07
    adge
    -0.07
     Earn
    -0.07
    sg
    -0.07
    ='{$
    -0.07
    yh
    -0.06
    .btnClose
    -0.06
    POSITIVE LOGITS
     maybe
    0.06
    odon
    0.06
     probably
    0.06
     thinking
    0.06
    odium
    0.06
     recently
    0.05
    ynet
    0.05
    pars
    0.05
     rows
    0.05
    574
    0.05
    Activations Density 0.041%

    No Known Activations