© 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 (Instruct)
    3. 50-RESID-POST-GF
    4. 38532
    Prev
    Next
    INDEX
    Explanations

    has deposited

    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
    .enterprise
    -0.11
    ilib
    -0.10
    CTR
    -0.09
    -tank
    -0.09
     Tank
    -0.09
     Tanks
    -0.09
    èĦ
    -0.09
     Tillerson
    -0.09
     Slots
    -0.09
     agitation
    -0.09
    POSITIVE LOGITS
     Robin
    0.19
     margin
    0.18
     Schw
    0.18
     trading
    0.16
    Robin
    0.16
     Margin
    0.16
     execution
    0.16
     custody
    0.15
     account
    0.15
     cust
    0.15
    Activations Density 0.065%

    No Known Activations