© 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. 26810
    Prev
    Next
    INDEX
    Explanations

    what things do

    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
     Happ
    -0.11
    ted
    -0.11
    970
    -0.09
     Bey
    -0.09
    eron
    -0.09
    685
    -0.09
    osl
    -0.09
    opor
    -0.09
    aran
    -0.09
    UTH
    -0.09
    POSITIVE LOGITS
     doing
    0.19
    åģļ
    0.17
     Doing
    0.17
    doing
    0.17
    Doing
    0.16
    å¹¹
    0.13
     accompl
    0.12
     capable
    0.12
    Purpose
    0.11
     does
    0.11
    Activations Density 0.069%

    No Known Activations