© 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. 17-LLAMASCOPE-RES-131K
    11. 105741
    Prev
    Next
    INDEX
    Explanations

    connections to women and their contributions in various contexts

    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
    ixo
    -0.07
    983
    -0.06
    n
    -0.06
    鼶
    -0.06
    -0.06
    ñas
    -0.06
    ues
    -0.06
    987
    -0.06
    v
    -0.06
    908
    -0.06
    POSITIVE LOGITS
    ebo
    0.09
    DAQ
    0.08
    idata
    0.07
    arde
    0.07
    defgroup
    0.07
    agnost
    0.07
    ereco
    0.07
    issing
    0.07
    rib
    0.07
    otime
    0.07
    Activations Density 0.003%

    No Known Activations