© 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. 35427
    Prev
    Next
    INDEX
    Explanations

    ir and its continuations

    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
    Fi
    -0.10
    kea
    -0.09
     unst
    -0.09
    eba
    -0.09
    innie
    -0.08
    acious
    -0.08
     Dudley
    -0.08
    ipsis
    -0.08
    ey
    -0.08
    ipy
    -0.08
    POSITIVE LOGITS
     ir
    0.16
     Ir
    0.15
    (IR
    0.14
    ány
    0.13
    regular
    0.13
    replace
    0.12
    licht
    0.12
    ancell
    0.12
    ónico
    0.12
    (ir
    0.12
    Activations Density 0.030%

    No Known Activations