© 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 EvalsExportsAPI 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. 88758
    Prev
    Next
    INDEX
    Explanations

    instances of legal and regulatory citations

    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
    unden
    -0.08
    AtPath
    -0.07
    AreaView
    -0.07
    icas
    -0.07
    ught
    -0.07
    uguay
    -0.06
    amu
    -0.06
    .gdx
    -0.06
    amon
    -0.06
    rated
    -0.06
    POSITIVE LOGITS
    /../
    0.07
     Commons
    0.06
     TU
    0.06
    /off
    0.06
    "].(
    0.06
     Oc
    0.06
     Off
    0.06
     MainForm
    0.06
    TU
    0.06
     dur
    0.05
    Activations Density 0.009%

    No Known Activations