© 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. 969
    Prev
    Next
    INDEX
    Explanations

    10, ten, 100, 200, 55, 108

    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
    hex
    -0.09
    ＿＿
    -0.09
    atro
    -0.09
    spa
    -0.09
     :::
    -0.08
    aises
    -0.08
     constit
    -0.08
     âĸ¼
    -0.08
    ves
    -0.08
     quart
    -0.08
    POSITIVE LOGITS
     ten
    0.26
     tenth
    0.22
     Ten
    0.21
    10
    0.21
     TEN
    0.20
    åįģ
    0.19
     деÑģÑı
    0.19
    Ten
    0.19
    ten
    0.18
    _ten
    0.16
    Activations Density 0.123%

    No Known Activations