© 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. 77163
    Prev
    Next
    INDEX
    Explanations

    phrases that convey skepticism or criticism

    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
     geil
    -0.08
     fik
    -0.07
    StackNavigator
    -0.07
    ChangeEvent
    -0.07
    odega
    -0.07
    quist
    -0.07
    (æĹ¥
    -0.07
    ковой
    -0.06
    IGO
    -0.06
    .await
    -0.06
    POSITIVE LOGITS
     lecture
    0.09
     lect
    0.08
     credibility
    0.08
     Authority
    0.07
     authority
    0.07
     lectures
    0.07
    actory
    0.07
     Moran
    0.06
     qualified
    0.06
     crit
    0.06
    Activations Density 0.035%

    No Known Activations