© 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. 49620
    Prev
    Next
    INDEX
    Explanations

    super followed by something (e.g., ior, ficie, color, surpasses)

    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
    sys
    -0.10
    ï¾ĺ
    -0.09
     Rowe
    -0.09
    inned
    -0.09
    917
    -0.09
    953
    -0.09
    ERM
    -0.09
     Lam
    -0.09
    seau
    -0.08
    obel
    -0.08
    POSITIVE LOGITS
    è¶Ĭ
    0.15
     over
    0.13
    iors
    0.12
    ior
    0.12
     overcome
    0.12
    bia
    0.11
    drive
    0.11
    åħĭ
    0.11
    éģİ
    0.11
    enal
    0.11
    Activations Density 0.015%

    No Known Activations