© 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. 94029
    Prev
    Next
    INDEX
    Explanations

    references to trolling or parodying behaviors

    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
    ÑĢÑĥд
    -0.07
    Ñĩик
    -0.07
    ÏĨÏĮ
    -0.07
    velt
    -0.06
     fore
    -0.06
    ahl
    -0.06
    Fore
    -0.06
    disposing
    -0.06
    oose
    -0.06
    μÏĮ
    -0.06
    POSITIVE LOGITS
     joke
    0.13
     satire
    0.12
     mock
    0.12
     jest
    0.11
     joking
    0.11
    /mock
    0.11
     Mock
    0.10
     sarc
    0.10
     jokes
    0.10
     tongue
    0.10
    Activations Density 0.043%

    No Known Activations