© 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 EvalsExportsinterp-engineNEWAPI 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. 124686
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service and satisfaction

    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
     --------------------------------------------------------------------------↵
    -0.08
    oppins
    -0.07
    ObjectOfType
    -0.07
    ESCO
    -0.07
    AFF
    -0.06
     manned
    -0.06
    .createFrom
    -0.06
    oles
    -0.06
    _visitor
    -0.06
    atoi
    -0.06
    POSITIVE LOGITS
     Baths
    0.07
     Eag
    0.06
    igo
    0.06
    lopedia
    0.06
     Jah
    0.06
     inse
    0.06
     Slee
    0.06
     patch
    0.06
    yla
    0.06
    .patch
    0.06
    Activations Density 0.001%

    No Known Activations