© 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. 38021
    Prev
    Next
    INDEX
    Explanations

    estate and executor terms

    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
    @Id
    -0.10
     past
    -0.10
     prec
    -0.09
     Trials
    -0.09
    adier
    -0.09
    oldown
    -0.09
     listener
    -0.09
     divorced
    -0.09
     WARRANT
    -0.08
     Listener
    -0.08
    POSITIVE LOGITS
     testament
    0.25
     intest
    0.22
     estate
    0.21
     Testament
    0.21
    éģº
    0.20
    estate
    0.20
     exec
    0.19
    éģĹ
    0.19
    executor
    0.18
    Executor
    0.18
    Activations Density 0.047%

    No Known Activations