© 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. 33470
    Prev
    Next
    INDEX
    Explanations

    succubus, succinct, succulent

    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
    lio
    -0.12
    ufen
    -0.10
    undef
    -0.09
    ãģĬãĤĬ
    -0.09
     femin
    -0.09
    ÑĪÑĤ
    -0.09
    rence
    -0.09
     Peel
    -0.09
    stk
    -0.09
    enda
    -0.08
    POSITIVE LOGITS
     succ
    0.21
     Succ
    0.21
    succ
    0.18
    umbed
    0.16
    umbing
    0.16
    inct
    0.15
    ursal
    0.14
    ulent
    0.14
    cess
    0.12
    inate
    0.11
    Activations Density 0.028%

    No Known Activations