© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33920
    Prev
    Next
    INDEX
    Explanations

    fictional AI assistant

    np_acts-logits-general · gemini-2.5-flash-lite

    instructions and formatting cues related to chatbot roleplay/meta-conversation, especially second-person prompts addressing an AI and assistant-style header markers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heller
    -0.10
    j
    -0.10
     Kling
    -0.09
    angi
    -0.09
    rs
    -0.09
    instr
    -0.09
     Gors
    -0.09
    warts
    -0.09
     mutate
    -0.09
    f
    -0.08
    POSITIVE LOGITS
     AI
    0.16
    AI
    0.13
     artificial
    0.12
     entity
    0.11
     system
    0.11
     machine
    0.11
     ai
    0.11
     interface
    0.10
    scp
    0.10
    Override
    0.10
    Activations Density 0.294%

    No Known Activations