© 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. 130989
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and dissatisfaction related to governance or public policy

    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
    znam
    -0.08
    -ng
    -0.08
    AttributeValue
    -0.08
    бÑĥдÑĮ
    -0.08
    LayoutConstraint
    -0.07
    .gdx
    -0.07
    avig
    -0.07
    agma
    -0.07
    adiens
    -0.07
    inke
    -0.07
    POSITIVE LOGITS
     perceived
    0.11
     perception
    0.09
     perceptions
    0.08
     perceive
    0.08
     felt
    0.08
     feeling
    0.07
     popular
    0.07
     feelings
    0.07
     opinion
    0.07
     many
    0.07
    Activations Density 0.064%

    No Known Activations