© 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. 83742
    Prev
    Next
    INDEX
    Explanations

    terms related to education and gender

    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
    lef
    -0.08
    ypad
    -0.07
    arak
    -0.07
    maid
    -0.07
    wrapped
    -0.07
    kest
    -0.07
    ovánÃŃm
    -0.07
    leh
    -0.07
    ESC
    -0.07
    kea
    -0.07
    POSITIVE LOGITS
     genders
    0.07
    æĢ§
    0.07
     nature
    0.07
     gender
    0.07
    usta
    0.07
    hed
    0.07
    321
    0.06
    atoi
    0.06
    239
    0.06
    971
    0.06
    Activations Density 0.003%

    No Known Activations