© 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. 127270
    Prev
    Next
    INDEX
    Explanations

    names and references related to women, particularly in contexts of authorship or creativity

    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
    аÑĢам
    -0.08
    éŀ
    -0.07
    ctica
    -0.07
    ãĥķãĥ¬
    -0.07
    vant
    -0.07
    aset
    -0.07
    pus
    -0.07
    quip
    -0.06
    thur
    -0.06
    erah
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĥĦ
    0.06
    ẫ
    0.06
    les
    0.06
     Extended
    0.06
    -deals
    0.06
     âĨĴ↵↵
    0.05
    erialize
    0.05
    ers
    0.05
    -haspopup
    0.05
    Ñģен
    0.05
    Activations Density 0.030%

    No Known Activations