© 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. 44415
    Prev
    Next
    INDEX
    Explanations

    delete or clear browsing data

    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
     Nack
    -0.10
    CurrentValue
    -0.10
    isson
    -0.10
     ping
    -0.09
     rew
    -0.09
     Lucy
    -0.09
    zers
    -0.09
    anke
    -0.09
     tog
    -0.09
     Baum
    -0.09
    POSITIVE LOGITS
     cookies
    0.31
     Cookies
    0.26
     cookie
    0.24
    cookies
    0.23
    Cookies
    0.23
     cache
    0.20
    cookie
    0.19
     Cookie
    0.19
     history
    0.18
    Cookie
    0.18
    Activations Density 0.031%

    No Known Activations