© 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. 87205
    Prev
    Next
    INDEX
    Explanations

    names and terms associated with humor and comedy figures

    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
    ing
    -0.07
    ello
    -0.07
    nee
    -0.07
    ilar
    -0.07
    ulti
    -0.07
    agens
    -0.06
    erea
    -0.06
    akistan
    -0.06
    ilon
    -0.06
    пон
    -0.06
    POSITIVE LOGITS
    üstü
    0.08
    ault
    0.07
    autop
    0.07
    ãĤ¸ãĤª
    0.07
    bast
    0.07
    .scalablytyped
    0.07
    åıĶ
    0.06
    aux
    0.06
     deflect
    0.06
     sert
    0.06
    Activations Density 0.001%

    No Known Activations