© 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. 54945
    Prev
    Next
    INDEX
    Explanations

    dystopian future or record low

    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
     crappy
    -0.17
     fools
    -0.15
     dope
    -0.13
     fart
    -0.11
     crap
    -0.11
     derp
    -0.11
    ãĢĢï¾Ĭ
    -0.10
     sucker
    -0.09
     rubbish
    -0.09
     thang
    -0.09
    POSITIVE LOGITS
     god
    0.32
     fucking
    0.30
     Fucking
    0.25
     eff
    0.22
    god
    0.20
    ucking
    0.19
     cazzo
    0.19
     fuck
    0.18
     fr
    0.18
    dam
    0.18
    Activations Density 0.125%

    No Known Activations