© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 60401
    Prev
    Next
    INDEX
    Explanations

    arg followed by o, ment, or entina

    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
    룬
    -0.11
    ets
    -0.10
    ETS
    -0.10
    etten
    -0.10
     Remed
    -0.09
    acers
    -0.09
    ET
    -0.09
     Allan
    -0.09
    ERAL
    -0.09
    erald
    -0.08
    POSITIVE LOGITS
    ÑĥменÑĤ
    0.22
    UMENT
    0.19
    oment
    0.19
    uably
    0.18
    inine
    0.14
    (Arg
    0.14
    onaut
    0.13
    atro
    0.13
     Arg
    0.13
    umen
    0.12
    Activations Density 0.027%

    No Known Activations