© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36150
    Prev
    Next
    INDEX
    Explanations

    ban, banned, prohibition

    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
    udas
    -0.12
     uncon
    -0.10
    nez
    -0.10
     withheld
    -0.10
     exempt
    -0.09
     strife
    -0.09
    asser
    -0.09
     Counter
    -0.09
    oss
    -0.09
    olet
    -0.09
    POSITIVE LOGITS
     ban
    0.49
    ç¦ģæŃ¢
    0.45
    ban
    0.37
     Ban
    0.36
     bans
    0.35
    Ban
    0.35
    ç¦ģ
    0.35
     prohibition
    0.32
     banned
    0.31
     ç¦
    0.29
    Activations Density 0.184%

    No Known Activations