© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 34780
    Prev
    Next
    INDEX
    Explanations

    asking or telling

    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
     contacting
    -0.16
     contacted
    -0.15
     contact
    -0.12
     contacto
    -0.11
     Kontakt
    -0.11
     Contact
    -0.11
     contacts
    -0.11
     kontakt
    -0.11
    contact
    -0.10
     calling
    -0.10
    POSITIVE LOGITS
     ask
    0.20
     explain
    0.16
     they
    0.16
     explained
    0.15
     asked
    0.15
     tell
    0.14
    ask
    0.14
     They
    0.14
    They
    0.13
    Ask
    0.13
    Activations Density 0.054%

    No Known Activations