© 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. 85236
    Prev
    Next
    INDEX
    Explanations

    terms related to reproductive choices and women's health

    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
    ekil
    -0.07
    infeld
    -0.07
    ayer
    -0.07
     Damen
    -0.06
    ligne
    -0.06
    हल
    -0.06
     menstr
    -0.06
    aben
    -0.06
    uddenly
    -0.06
    RuntimeObject
    -0.06
    POSITIVE LOGITS
    unch
    0.06
     Genetic
    0.06
     guaranteed
    0.06
    etch
    0.06
     pro
    0.06
    intree
    0.06
    ect
    0.06
     genetic
    0.05
     consequat
    0.05
    InBackground
    0.05
    Activations Density 0.000%

    No Known Activations