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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21979
    Prev
    Next
    INDEX
    Explanations

    extract and process

    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
     harvested
    -0.13
    éĩĩ
    -0.12
    æĬĵ
    -0.11
    æijĺ
    -0.11
     pickup
    -0.11
     pickups
    -0.10
     abducted
    -0.10
     confiscated
    -0.10
     picked
    -0.10
     picks
    -0.10
    POSITIVE LOGITS
    åĬłå·¥
    0.13
     store
    0.13
     storing
    0.12
     stored
    0.12
     processed
    0.12
     processing
    0.11
    åŃĺäºİ
    0.10
     almacen
    0.10
    oise
    0.10
    vů
    0.10
    Activations Density 0.110%

    No Known Activations