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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58326
    Prev
    Next
    INDEX
    Explanations

    assistant roles or AI identity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ôn
    -0.09
    uits
    -0.08
    rink
    -0.08
     Ras
    -0.08
     Trib
    -0.08
     lasting
    -0.08
     âĶĢ
    -0.08
    æ³¥
    -0.08
    opes
    -0.08
     Lyons
    -0.08
    POSITIVE LOGITS
     role
    0.13
    rompt
    0.11
    å¸Ń
    0.11
    ship
    0.10
     Äijỡ
    0.10
     AI
    0.10
     roles
    0.10
    .djang
    0.09
    ships
    0.09
    ive
    0.09
    Activations Density 0.091%

    No Known Activations