© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77373
    Prev
    Next
    INDEX
    Explanations

    phrases related to humor and wordplay

    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
    ilities
    -0.07
     Ninh
    -0.06
    ãĢħ
    -0.06
    ocator
    -0.06
    anus
    -0.06
    ãĥĮ
    -0.06
    lied
    -0.06
    -beta
    -0.06
    MethodName
    -0.06
     getattr
    -0.06
    POSITIVE LOGITS
    inth
    0.07
    ascus
    0.07
    echo
    0.07
    ä¸įåŃĺåľ¨
    0.06
    ucci
    0.06
    net
    0.06
    pan
    0.06
     observers
    0.06
     lonely
    0.06
     anv
    0.06
    Activations Density 0.001%

    No Known Activations