© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1343
    Prev
    Next
    INDEX
    Explanations

    concepts related to biochemical processes and their significance in viral infections

    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
    uci
    -0.08
    nict
    -0.07
    รà¸ĵ
    -0.07
    ÎĦ
    -0.07
    hiba
    -0.07
    cak
    -0.07
    iddi
    -0.07
    enci
    -0.07
    墨
    -0.07
     geil
    -0.07
    POSITIVE LOGITS
     contribution
    0.07
     somewhere
    0.07
     m
    0.07
     contributions
    0.06
     dispens
    0.06
     Contribution
    0.06
     Contributions
    0.06
     absolutely
    0.06
    427
    0.06
     neither
    0.06
    Activations Density 0.026%

    No Known Activations