© 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. 54505
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate origins or associations related to people or groups

    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
    ä¸įäºĨ
    -0.08
    avel
    -0.07
    avan
    -0.07
     ï½ŀ
    -0.07
     Antar
    -0.07
    /../
    -0.07
    nÄĽji
    -0.06
    ihan
    -0.06
    ä¿ĥ
    -0.06
     blockSize
    -0.06
    POSITIVE LOGITS
     across
    0.12
     throughout
    0.10
     around
    0.09
     backgrounds
    0.08
     both
    0.08
     everywhere
    0.08
     walks
    0.07
     diverse
    0.07
     whom
    0.07
     McCl
    0.07
    Activations Density 0.015%

    No Known Activations