© 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. 17-LLAMASCOPE-RES-131K
    11. 124938
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional service and advice

    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
    á»įng
    -0.08
    uell
    -0.08
    ieux
    -0.08
    eyse
    -0.07
    ukkit
    -0.07
    kup
    -0.07
    meli
    -0.07
    emic
    -0.07
    igan
    -0.07
    íĦ
    -0.07
    POSITIVE LOGITS
     whilst
    0.07
     while
    0.06
     Pearson
    0.06
    enu
    0.06
     etc
    0.06
    etc
    0.06
    etre
    0.06
     until
    0.06
     Pro
    0.06
     thereby
    0.06
    Activations Density 0.250%

    No Known Activations