© 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. 60885
    Prev
    Next
    INDEX
    Explanations

    ps followed by numbers or specific suffixes

    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
    oftware
    -0.12
    essel
    -0.10
    ettings
    -0.09
    acob
    -0.09
    pez
    -0.09
    å¿
    -0.09
    ign
    -0.08
    etler
    -0.08
    пеÑĩ
    -0.08
    ety
    -0.08
    POSITIVE LOGITS
    oriasis
    0.17
     ps
    0.15
    ued
    0.15
     Ps
    0.15
    ych
    0.13
    (ps
    0.13
    wich
    0.12
    ps
    0.11
    yll
    0.11
    ycop
    0.11
    Activations Density 0.031%

    No Known Activations