© 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. 34017
    Prev
    Next
    INDEX
    Explanations

    expected or scheduled events

    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
    æŃ£åľ¨
    -0.12
     envis
    -0.11
     pending
    -0.09
     Äijang
    -0.09
     nearing
    -0.09
     Pending
    -0.09
     ongoing
    -0.09
     forthcoming
    -0.08
    icles
    -0.08
    441
    -0.08
    POSITIVE LOGITS
     expected
    0.27
    expected
    0.22
     Expected
    0.20
    Expected
    0.19
     scheduled
    0.19
    .expected
    0.18
     due
    0.17
     likely
    0.16
    scheduled
    0.16
    cheduled
    0.15
    Activations Density 0.077%

    No Known Activations