© 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. 714
    Prev
    Next
    INDEX
    Explanations

    journal archives system

    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
     Closet
    -0.10
    .RightToLeft
    -0.09
    ECTOR
    -0.09
     ï¾ĺ
    -0.08
     Vincent
    -0.08
     friendships
    -0.08
    æ²
    -0.08
    forge
    -0.08
    elp
    -0.08
    ayment
    -0.08
    POSITIVE LOGITS
     records
    0.38
     record
    0.26
     database
    0.26
    records
    0.25
     system
    0.24
     Records
    0.24
     systems
    0.23
    æķ°æį®åºĵ
    0.22
    Records
    0.20
    _records
    0.19
    Activations Density 0.130%

    No Known Activations