© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 92715
    Prev
    Next
    INDEX
    Explanations

    instances of parental concern regarding children's screen time and media consumption

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

    Formatting elements like periods, line breaks, or other punctuation that separate distinct items in lists, policy documents, or structured 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
    ishi
    -0.06
    wdx
    -0.06
     %[
    -0.06
    remen
    -0.06
    .il
    -0.06
    olicitud
    -0.06
     ExecutionContext
    -0.06
    ed
    -0.06
     Göz
    -0.06
     Edmund
    -0.06
    POSITIVE LOGITS
     when
    0.09
     your
    0.07
    when
    0.07
    DMI
    0.06
     When
    0.06
     you
    0.06
     cuando
    0.06
    _when
    0.06
    Your
    0.06
     being
    0.06
    Activations Density 0.006%

    No Known Activations