© 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. 22-LLAMASCOPE-RES-131K
    11. 3946
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative expressions indicating increases or decreases in intensity or quantity

    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
     jab
    -0.06
    âĢª
    -0.06
    311
    -0.06
    oir
    -0.06
    à¹ĩà¸Ķ
    -0.06
    ynes
    -0.05
     vos
    -0.05
    021
    -0.05
    ÑĥÑħ
    -0.05
    ais
    -0.05
    POSITIVE LOGITS
    -and
    0.18
    _and
    0.13
     and
    0.13
    &S
    0.12
     &
    0.11
    and
    0.10
    åĴĮ
    0.10
    &T
    0.09
    &D
    0.09
     и
    0.09
    Activations Density 0.053%

    No Known Activations