© 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. 16025
    Prev
    Next
    INDEX
    Explanations

    words ending in -ment, -ny, -ation, -ity, -ial, -ary

    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
    loys
    -0.11
    emmel
    -0.10
    eck
    -0.09
     rearr
    -0.09
    ÂŃt
    -0.09
    nex
    -0.09
    flater
    -0.08
     Spr
    -0.08
    i
    -0.08
    iability
    -0.08
    POSITIVE LOGITS
    wide
    0.11
     Lamp
    0.10
    ABLE
    0.10
    able
    0.10
    ation
    0.10
    ogeneous
    0.09
    utive
    0.09
     Env
    0.09
    aneous
    0.09
     Boeh
    0.09
    Activations Density 0.144%

    No Known Activations