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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44734
    Prev
    Next
    INDEX
    Explanations

    select, scroll, tap, choose

    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
    odata
    -0.10
     Navigate
    -0.10
     Barker
    -0.10
     navigator
    -0.09
    ubl
    -0.09
     Visit
    -0.09
    ạn
    -0.09
    å°º
    -0.09
     Hanna
    -0.09
    ws
    -0.09
    POSITIVE LOGITS
     select
    0.25
     then
    0.19
    select
    0.17
     scroll
    0.15
     choose
    0.15
    Select
    0.15
    .select
    0.14
     selects
    0.13
     search
    0.13
    then
    0.13
    Activations Density 0.043%

    No Known Activations