© 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. 126689
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional or humorous expressions

    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
    jedn
    -0.07
    azu
    -0.07
    âu
    -0.07
    èo
    -0.07
    vation
    -0.07
    OfYear
    -0.07
    uml
    -0.07
    orest
    -0.07
    ifecycle
    -0.07
    geois
    -0.07
    POSITIVE LOGITS
     Ones
    0.06
     ones
    0.06
    ie
    0.06
     they
    0.06
    o
    0.06
     Boeh
    0.06
    inand
    0.06
    es
    0.06
    furt
    0.06
     Roe
    0.06
    Activations Density 0.135%

    No Known Activations