© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33694
    Prev
    Next
    INDEX
    Explanations

    noticing or not realizing

    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
     çĻ
    -0.10
     acquaint
    -0.10
    ÙĪØ«
    -0.09
    898
    -0.09
     acquaintance
    -0.09
     pent
    -0.09
     Fam
    -0.08
    015
    -0.08
    afort
    -0.08
     acquainted
    -0.08
    POSITIVE LOGITS
     notice
    0.23
     suspect
    0.22
     noticed
    0.20
    åıijçİ°
    0.19
     discover
    0.19
     notices
    0.19
     suspicions
    0.19
     discovery
    0.19
     suspects
    0.19
     suspicion
    0.18
    Activations Density 0.043%

    No Known Activations