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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26360
    Prev
    Next
    INDEX
    Explanations

    interactions and expressions of uncertainty or help-seeking in a conversational context

    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
     Vintage
    -0.06
    Vintage
    -0.06
    ambda
    -0.06
     ash
    -0.06
    ancer
    -0.06
    peria
    -0.06
    озÑı
    -0.06
     Dob
    -0.06
    urring
    -0.05
    erdale
    -0.05
    POSITIVE LOGITS
     bounty
    0.08
     answer
    0.08
    Closure
    0.07
    ckt
    0.07
     closure
    0.07
     answered
    0.07
     Closure
    0.07
     Answer
    0.07
    answer
    0.06
    ISR
    0.06
    Activations Density 0.008%

    No Known Activations