© 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. 107635
    Prev
    Next
    INDEX
    Explanations

    specific high-impact political proposals or actions

    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
    uggle
    -0.07
    ÑĢап
    -0.07
    rost
    -0.07
    axy
    -0.06
    robe
    -0.06
    icz
    -0.06
    ">ÃĹ</
    -0.06
    ANNER
    -0.06
    ož
    -0.06
    óa
    -0.06
    POSITIVE LOGITS
    iani
    0.07
    final
    0.07
    _firestore
    0.07
    motion
    0.06
     rat
    0.06
    dash
    0.06
     Improved
    0.06
    mek
    0.06
     Final
    0.06
     Env
    0.06
    Activations Density 0.001%

    No Known Activations