© 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. 55476
    Prev
    Next
    INDEX
    Explanations

    references to women and their roles in historical 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
    ÑĨ
    -0.07
    amedi
    -0.07
    NonQuery
    -0.06
    _lineno
    -0.06
    åĪĢ
    -0.06
    atab
    -0.06
     Ze
    -0.06
    ucch
    -0.06
    ablish
    -0.06
    ButtonModule
    -0.06
    POSITIVE LOGITS
    194
    0.07
    oden
    0.07
     trail
    0.07
     Trail
    0.06
     work
    0.06
    anky
    0.06
    rieg
    0.06
     contributions
    0.06
    ape
    0.06
    ź
    0.06
    Activations Density 0.005%

    No Known Activations