© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 63981
    Prev
    Next
    INDEX
    Explanations

    FTL: Faster Than Light

    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
    VIRTUAL
    -0.10
    èĤ²
    -0.10
     virtual
    -0.10
     meshes
    -0.10
    Textures
    -0.10
    éĤ¦
    -0.09
    ASA
    -0.09
     Kush
    -0.09
     deduct
    -0.09
     prompt
    -0.09
    POSITIVE LOGITS
     bosses
    0.17
     Terraria
    0.16
     boss
    0.13
     Boss
    0.12
    Boss
    0.12
    boss
    0.11
     minib
    0.10
     shooting
    0.10
     Corruption
    0.10
    leared
    0.09
    Activations Density 0.048%

    No Known Activations