© 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. 44710
    Prev
    Next
    INDEX
    Explanations

    çļĦåıįåºĶ, éĺ»æĿ¥

    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
    ãĥ¾
    -0.10
     ãĢĪ
    -0.09
    pty
    -0.09
    icket
    -0.09
     Amit
    -0.09
     particul
    -0.08
     dy
    -0.08
    çļĦäºĭæĥħ
    -0.08
     Scenario
    -0.08
     Area
    -0.08
    POSITIVE LOGITS
     grads
    0.12
    ãĢĤwww
    0.10
    ï¼ĮåŃĺäºİ
    0.10
    太éĺ³åŁİ
    0.09
    @Web
    0.09
     obvious
    0.09
    åħ¶
    0.09
    thest
    0.09
    pls
    0.09
    ãĢĤč\n
    0.09
    Activations Density 0.160%

    No Known Activations