© 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. 84646
    Prev
    Next
    INDEX
    Explanations

    instances of joking 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
    orges
    -0.07
    elig
    -0.07
    iki
    -0.07
    afil
    -0.06
    ÑĥÑĩа
    -0.06
    ddit
    -0.06
    ÙĪاج
    -0.06
    ur
    -0.06
    elu
    -0.06
    ukt
    -0.06
    POSITIVE LOGITS
    ghan
    0.07
    atures
    0.06
    ingly
    0.06
    verted
    0.06
    галÑĸ
    0.06
    burg
    0.06
    bone
    0.06
    ikat
    0.06
    ê¼
    0.06
     plural
    0.06
    Activations Density 0.004%

    No Known Activations