© 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. 106156
    Prev
    Next
    INDEX
    Explanations

    elements of humor or laughter in conversations

    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
    pering
    -0.07
    ÙĦÙĥ
    -0.06
    IBUTES
    -0.06
    nown
    -0.06
    asher
    -0.06
    licted
    -0.06
    anner
    -0.06
    iego
    -0.06
    itis
    -0.06
    axed
    -0.06
    POSITIVE LOGITS
    ellan
    0.08
    غÙĦ
    0.06
    æĭį
    0.06
    sic
    0.06
    gest
    0.06
     Stafford
    0.06
    ding
    0.06
     mim
    0.06
    .simps
    0.06
     wand
    0.06
    Activations Density 0.011%

    No Known Activations