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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77587
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or questions about opinions and beliefs

    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
    angu
    -0.07
    ream
    -0.07
    uely
    -0.07
    лл
    -0.07
    елем
    -0.06
    SID
    -0.06
    ango
    -0.06
    ahr
    -0.06
    nee
    -0.06
    /site
    -0.06
    POSITIVE LOGITS
     maybe
    0.10
    maybe
    0.09
    Maybe
    0.08
     Maybe
    0.08
    just
    0.07
     dun
    0.07
     MAY
    0.07
     just
    0.07
     perhaps
    0.07
    Just
    0.07
    Activations Density 0.054%

    No Known Activations