© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 87259
    Prev
    Next
    INDEX
    Explanations

    questions related to societal and ethical dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The double question mark "?" appears at the end of questions, often rhetorical ones. These questions typically challenge assumptions, invite reflection, or pose thought-provoking inquiries within various texts including blogs, articles, and educational content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    eil
    -0.07
    εÏģγ
    -0.07
    rchive
    -0.07
     rost
    -0.07
    ctl
    -0.07
    umer
    -0.07
    zend
    -0.07
    AspNet
    -0.06
    Ù
    -0.06
    /vnd
    -0.06
    POSITIVE LOGITS
     yes
    0.12
     Yes
    0.12
     YES
    0.12
    Yes
    0.11
    yes
    0.10
     Nope
    0.10
    YES
    0.10
    “Yes
    0.09
    "Yes
    0.09
     oui
    0.08
    Activations Density 0.061%

    No Known Activations