© 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. 29620
    Prev
    Next
    INDEX
    Explanations

    cryptographic algorithms and security

    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
     Decrypt
    -0.15
    Decrypt
    -0.14
     decrypted
    -0.13
     encrypted
    -0.13
    encrypted
    -0.12
     decrypt
    -0.12
    ryn
    -0.12
    cipher
    -0.11
    Cipher
    -0.11
    decrypt
    -0.11
    POSITIVE LOGITS
     security
    0.22
     secure
    0.18
    security
    0.17
     resistance
    0.16
     Security
    0.15
    -security
    0.15
     prov
    0.15
     Resistance
    0.14
     resistant
    0.14
     schemes
    0.14
    Activations Density 0.071%

    No Known Activations