© 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
    5. 50-RESID-POST-GF
    7. 33939
    Prev
    Next
    INDEX
    Explanations

    events and occurrences

    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
    iesen
    -0.09
     Gala
    -0.09
    rupted
    -0.09
     Mori
    -0.09
     penn
    -0.08
     thú
    -0.08
    508
    -0.08
     EntityManager
    -0.08
     Tob
    -0.08
     Eh
    -0.08
    POSITIVE LOGITS
     events
    0.57
     event
    0.50
    äºĭ件
    0.45
    events
    0.42
     Events
    0.42
     eventos
    0.38
    event
    0.37
     evento
    0.36
    Events
    0.36
    -events
    0.35
    Activations Density 0.149%

    No Known Activations