© 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. 44462
    Prev
    Next
    INDEX
    Explanations

    call

    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
    airs
    -0.08
     Chat
    -0.08
    Chat
    -0.08
     Teh
    -0.07
     reck
    -0.07
     Cum
    -0.07
    toHave
    -0.07
     Iter
    -0.07
     Neal
    -0.07
    738
    -0.07
    POSITIVE LOGITS
     call
    0.85
     calls
    0.72
    call
    0.66
     calling
    0.65
     Call
    0.62
     CALL
    0.60
    -call
    0.59
    Call
    0.58
     Calls
    0.56
    è°ĥçĶ¨
    0.56
    Activations Density 0.146%

    No Known Activations