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. 44828
    Prev
    Next
    INDEX
    Explanations

    bear of a man, very good

    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
    iế
    -0.09
    (MainActivity
    -0.08
    (UIAlertAction
    -0.08
    rchive
    -0.07
    >NN
    -0.07
    ¦¬
    -0.07
     ë¸
    -0.07
    ¶Į
    -0.07
    ĮĴ
    -0.07
    oldem
    -0.07
    POSITIVE LOGITS
    ize
    0.07
    iasi
    0.07
    uch
    0.06
    -m
    0.06
    als
    0.06
    anga
    0.06
     stran
    0.06
    lear
    0.06
    -type
    0.06
     ï¼į
    0.06
    Activations Density 0.036%

    No Known Activations