© 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. 40530
    Prev
    Next
    INDEX
    Explanations

    instances of communication and expressions of connection

    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
    issen
    -0.08
    uel
    -0.07
    ennen
    -0.07
    elon
    -0.07
    .walk
    -0.06
    åģ¥
    -0.06
     knot
    -0.06
    ikers
    -0.06
    .shell
    -0.06
     remar
    -0.06
    POSITIVE LOGITS
    952
    0.07
    703
    0.07
    316
    0.07
    powered
    0.06
    560
    0.06
     Lod
    0.06
    etric
    0.06
    ศาสà¸ķร
    0.06
    ìĤ¬ìĿ´
    0.06
     nhau
    0.06
    Activations Density 0.004%

    No Known Activations