© 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. 63275
    Prev
    Next
    INDEX
    Explanations

    Bourbon, boutiques, thorough

    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
     Maurit
    -0.11
    @"\n
    -0.10
    wives
    -0.09
    ären
    -0.09
    ogens
    -0.09
     pupper
    -0.09
     Jeh
    -0.09
    877
    -0.09
    ually
    -0.09
     mute
    -0.09
    POSITIVE LOGITS
    ing
    0.17
    ishment
    0.16
    ishing
    0.15
    a
    0.15
    y
    0.14
    agement
    0.13
    ished
    0.13
    tesy
    0.13
    ashtra
    0.13
    ney
    0.12
    Activations Density 0.068%

    No Known Activations