© 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. 49770
    Prev
    Next
    INDEX
    Explanations

    upper level sophisticated language

    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 (indirectly / hypothetically)

    No Comments

    Negative Logits
     vowels
    -0.11
     Lingu
    -0.10
     short
    -0.10
     lingu
    -0.10
     pronunciation
    -0.09
     Essence
    -0.09
    à¸ģà¸ķ
    -0.09
    appl
    -0.09
     gramm
    -0.08
     Wet
    -0.08
    POSITIVE LOGITS
     advanced
    0.15
     Advanced
    0.14
    Advanced
    0.14
     sentence
    0.14
    advanced
    0.13
     sophisticated
    0.13
     register
    0.13
    éģ£
    0.12
     niveau
    0.12
    idi
    0.12
    Activations Density 0.246%

    No Known Activations