© 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. 9-LLAMASCOPE-RES-131K
    11. 97113
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons related to health or financial statistics

    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
    eldon
    -0.06
     fed
    -0.06
    309
    -0.06
    zel
    -0.05
     Hoffman
    -0.05
     Bol
    -0.05
    oyal
    -0.05
    umont
    -0.05
     largely
    -0.05
    ziel
    -0.05
    POSITIVE LOGITS
    LAR
    0.07
    oÅĽci
    0.07
    Æ¡
    0.07
    Ø´ÙħاÙĦÛĮ
    0.07
    βά
    0.07
    &S
    0.07
    egg
    0.07
    лÑıв
    0.07
    èħ¹
    0.07
    ebek
    0.07
    Activations Density 0.011%

    No Known Activations