© 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. 128833
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or confusion in narratives

    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
    emas
    -0.06
    fid
    -0.06
     tension
    -0.06
     Dickens
    -0.06
    ç«ŀ
    -0.06
    ann
    -0.06
    olet
    -0.06
    DSL
    -0.05
    mpar
    -0.05
     competition
    -0.05
    POSITIVE LOGITS
    iParam
    0.07
    weg
    0.07
    oland
    0.07
     Hairst
    0.07
    \/\/
    0.07
    346
    0.07
    ä¹Ĺ
    0.07
    ¯u
    0.07
    ConfigurationException
    0.07
    getSingleton
    0.07
    Activations Density 0.000%

    No Known Activations