© 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 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. 118828
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and updates in a business 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
    oley
    -0.08
    olson
    -0.07
    imenti
    -0.07
     ngang
    -0.06
    elementType
    -0.06
    åĬ
    -0.06
    canf
    -0.06
    âĶĶ
    -0.06
    adies
    -0.06
    essim
    -0.06
    POSITIVE LOGITS
    edb
    0.06
    aed
    0.06
    yll
    0.06
     bree
    0.06
    yg
    0.06
    edla
    0.06
     IST
    0.06
    aged
    0.06
     interval
    0.06
    alla
    0.06
    Activations Density 0.000%

    No Known Activations