© 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. 69813
    Prev
    Next
    INDEX
    Explanations

    phrases related to chemicals and their interactions in a medical or scientific context

    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
    ito
    -0.06
    Ïħνα
    -0.06
    ITO
    -0.06
    Bulk
    -0.06
    Unused
    -0.06
     Barton
    -0.06
    anus
    -0.06
     Wikip
    -0.06
    fax
    -0.06
    kening
    -0.06
    POSITIVE LOGITS
    .qq
    0.06
    isdiction
    0.06
    synthesize
    0.06
    tplib
    0.06
    718
    0.05
     superior
    0.05
     WITHOUT
    0.05
     pocket
    0.05
     Kingdom
    0.05
    _without
    0.05
    Activations Density 0.000%

    No Known Activations