© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    locations after commas

    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
     neighborhood
    -0.11
    çĺ
    -0.10
     streets
    -0.10
     è£
    -0.10
     downtown
    -0.10
     neighbourhood
    -0.09
    etter
    -0.09
     sta
    -0.09
     STREET
    -0.09
     village
    -0.08
    POSITIVE LOGITS
     Greater
    0.29
     greater
    0.28
     suburbs
    0.26
    Greater
    0.26
    greater
    0.24
     suburban
    0.23
    éĥ
    0.21
     outskirts
    0.21
     suburb
    0.20
     outer
    0.17
    Activations Density 0.147%

    No Known Activations