© 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. 16318
    Prev
    Next
    INDEX
    Explanations

    this is water or too long

    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
    •FOX
    “No. absolutely not. Come here. You’re not going anywhere.”

    No Comments

    Negative Logits
    ady
    -0.09
    èĥŀ
    -0.09
    aviest
    -0.08
    intl
    -0.08
    halb
    -0.08
    owy
    -0.08
    DonaldTrump
    -0.08
    enty
    -0.08
    ipher
    -0.08
     ro
    -0.08
    POSITIVE LOGITS
     ifs
    0.11
    venes
    0.09
    uyen
    0.09
     ï¿£
    0.09
    tober
    0.09
    ÅĻej
    0.09
     ___
    0.09
    imizer
    0.09
     ____
    0.09
    ApiClient
    0.09
    Activations Density 0.207%

    No Known Activations