© 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. 45343
    Prev
    Next
    INDEX
    Explanations

    specific and fixed definitions

    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
    UIL
    -0.09
     dictates
    -0.08
    arta
    -0.08
    ès
    -0.08
    ÃŃda
    -0.08
     Garr
    -0.08
     conclusive
    -0.08
     preempt
    -0.08
    iggs
    -0.08
    ergy
    -0.08
    POSITIVE LOGITS
     specific
    0.53
     fixed
    0.40
     Specific
    0.37
     particular
    0.37
    specific
    0.36
    -specific
    0.35
     especÃŃf
    0.35
    åĽºå®ļ
    0.35
     bestimm
    0.33
     конкÑĢеÑĤ
    0.32
    Activations Density 0.323%

    No Known Activations