© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87967
    Prev
    Next
    INDEX
    Explanations

    phrases indicating subjective assessments or expressions of opinion

    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
    /respond
    -0.07
    aira
    -0.06
    ="__
    -0.06
     Ortiz
    -0.06
    utschein
    -0.06
     Scholarship
    -0.06
     yacc
    -0.06
    تÙĩا
    -0.06
    uracy
    -0.06
     kred
    -0.06
    POSITIVE LOGITS
     attempt
    0.10
     way
    0.08
    attempt
    0.08
     indication
    0.07
    ä¸Ģç§į
    0.07
     step
    0.07
     attempts
    0.07
    δή
    0.07
    æĿ¥èĩª
    0.07
     opportunity
    0.07
    Activations Density 0.046%

    No Known Activations