© 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. 34074
    Prev
    Next
    INDEX
    Explanations

    descriptive suffixes

    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
    iability
    -0.09
     Lois
    -0.09
     conf
    -0.09
    -Compatible
    -0.09
    anners
    -0.09
    actories
    -0.09
    íĨłíĨł
    -0.09
    sp
    -0.09
     beh
    -0.08
    azes
    -0.08
    POSITIVE LOGITS
    esome
    0.11
    áhl
    0.11
     Äijáo
    0.10
    ÑĤÑĶ
    0.10
    adel
    0.10
    isque
    0.10
    inous
    0.09
    ughty
    0.09
    acious
    0.09
    åħ¥åı£
    0.09
    Activations Density 0.142%

    No Known Activations