© 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. 105269
    Prev
    Next
    INDEX
    Explanations

    quotes or phrases that indicate direct speech or spoken thoughts

    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
    xm
    -0.07
     prostituer
    -0.07
    geç
    -0.07
    .semantic
    -0.07
    #${
    -0.07
    #echo
    -0.07
    ा:
    -0.07
     Yönetim
    -0.07
    ÙĪزÛĮ
    -0.07
     Truy
    -0.07
    POSITIVE LOGITS
    -urlencoded
    0.07
     Bart
    0.06
    optera
    0.06
    ipment
    0.06
    etting
    0.06
    odge
    0.06
    ittest
    0.05
    '
    0.05
    ial
    0.05
     Ih
    0.05
    Activations Density 0.009%

    No Known Activations