© 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. 83744
    Prev
    Next
    INDEX
    Explanations

    mentions of female wrestlers and their performances

    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
    illis
    -0.08
    Ìģt
    -0.07
    illus
    -0.07
    tah
    -0.07
    Uvs
    -0.07
    дам
    -0.07
    jsc
    -0.07
    ÃŃky
    -0.07
    egrity
    -0.07
    ÅĻeh
    -0.07
    POSITIVE LOGITS
     company
    0.07
     Story
    0.07
     Company
    0.07
    483
    0.07
    486
    0.06
    ìŀħ
    0.06
    Company
    0.06
    fat
    0.06
     story
    0.06
    -script
    0.06
    Activations Density 0.015%

    No Known Activations