© 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. 44501
    Prev
    Next
    INDEX
    Explanations

    affairs, sexual activity, process

    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
     resume
    -0.10
     rave
    -0.09
     nature
    -0.09
     backdrop
    -0.09
    GBK
    -0.09
    irse
    -0.08
    [js
    -0.08
     involvement
    -0.08
    neath
    -0.08
     contributions
    -0.08
    POSITIVE LOGITS
     affairs
    0.23
     effort
    0.17
     process
    0.17
     Affairs
    0.15
     loop
    0.15
     affair
    0.15
     conversation
    0.14
     activities
    0.13
     success
    0.13
    process
    0.13
    Activations Density 0.082%

    No Known Activations