© 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. 40754
    Prev
    Next
    INDEX
    Explanations

    explain, suggest, encourage, challenge

    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
    祥
    -0.10
    iry
    -0.09
    okit
    -0.09
    icont
    -0.09
     reinforces
    -0.09
     fir
    -0.09
     enlightened
    -0.09
    Å¡il
    -0.08
     Bold
    -0.08
    :::::|
    -0.08
    POSITIVE LOGITS
     challenge
    0.18
     challenges
    0.17
     encourage
    0.16
    challenge
    0.16
     invite
    0.15
    é¼ĵ
    0.14
    Challenge
    0.14
    è¿«
    0.14
     invit
    0.14
     encourages
    0.14
    Activations Density 0.074%

    No Known Activations