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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44936
    Prev
    Next
    INDEX
    Explanations

    color and subject matter descriptions

    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
    <|begin_of_text|>
    -0.08
     müc
    -0.08
    ³Øª
    -0.08
     deÄŁiÅŁ
    -0.08
    ¶Į
    -0.08
    ******č\n
    -0.08
     hatır
    -0.08
     kurtar
    -0.08
     deÄŁiÅŁtir
    -0.07
    ¦æĥħ
    -0.07
    POSITIVE LOGITS
     )\n\n\n\n\n\n\n\n
    0.10
     ragaz
    0.09
    ãĥ¼ãĥ¼
    0.08
     rac
    0.08
     damer
    0.08
     %[
    0.08
     Ally
    0.07
    ีà¹Ģà¸Ń
    0.07
    instanc
    0.07
     Meer
    0.07
    Activations Density 0.000%

    No Known Activations