© 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. 127710
    Prev
    Next
    INDEX
    Explanations

    representations of women in media and their diverse experiences

    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
    202
    -0.07
     ours
    -0.07
    ụn
    -0.06
     perhaps
    -0.06
    让æĪij
    -0.06
     whatever
    -0.06
     here
    -0.06
     information
    -0.06
    .Shared
    -0.06
    dob
    -0.06
    POSITIVE LOGITS
    arella
    0.07
    ByteBuffer
    0.06
    acci
    0.06
    prefer
    0.06
    porno
    0.06
     Twe
    0.05
     Concepts
    0.05
    iš
    0.05
    LayoutManager
    0.05
    ınızda
    0.05
    Activations Density 0.003%

    No Known Activations