© 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. 57468
    Prev
    Next
    INDEX
    Explanations

    tipo bruteforce

    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
    Encryption
    -0.11
    isser
    -0.10
    Encrypt
    -0.10
     Haram
    -0.10
    igy
    -0.10
     encrypt
    -0.10
    encrypt
    -0.09
    润
    -0.09
     Hust
    -0.09
     Cron
    -0.09
    POSITIVE LOGITS
     brut
    0.22
     Brut
    0.20
     cracking
    0.20
     guess
    0.20
     guessing
    0.19
    guess
    0.19
     brute
    0.19
     Guess
    0.18
    Guess
    0.17
     guesses
    0.17
    Activations Density 0.076%

    No Known Activations