Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34449
    Prev
    Next
    INDEX
    Explanations

    grinding, assistance, type, work, representation, process, chocolates

    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
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.09
    ¦æĥħ
    -0.09
    TRGL
    -0.08
    .Formatter
    -0.08
     -*-č\n
    -0.07
    Ðĭ
    -0.07
    šak
    -0.07
    \Events
    -0.07
    ¶Į
    -0.07
    .Directory
    -0.07
    POSITIVE LOGITS
     aforementioned
    0.10
     embod
    0.07
     guarante
    0.07
     safeg
    0.07
    SID
    0.07
     Pins
    0.06
    867
    0.06
    ob
    0.06
    Occurred
    0.06
    ppelin
    0.06
    Activations Density 0.601%

    No Known Activations