© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 84350
    Prev
    Next
    INDEX
    Explanations

    terms related to women's health and related advocacy efforts

    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
    amarin
    -0.08
    _aliases
    -0.07
    ziej
    -0.07
    olume
    -0.07
    vou
    -0.07
    lias
    -0.07
    sak
    -0.07
    fore
    -0.07
    kal
    -0.07
    rouch
    -0.06
    POSITIVE LOGITS
    غÙĦ
    0.07
    ìĸ¼
    0.07
     whom
    0.06
    ëĤĺ무
    0.06
    Msp
    0.06
    $__
    0.06
    /customer
    0.06
     alike
    0.06
    /preferences
    0.05
     Natal
    0.05
    Activations Density 0.165%

    No Known Activations