© 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. 38574
    Prev
    Next
    INDEX
    Explanations

    so that [pronoun] can

    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
    è¿Ļæł·çļĦ
    -0.09
    abr
    -0.09
    unga
    -0.09
     så
    -0.09
    sto
    -0.09
    ovo
    -0.09
    ming
    -0.09
    sthrough
    -0.08
    lib
    -0.08
     hy
    -0.08
    POSITIVE LOGITS
    aks
    0.20
    -called
    0.19
    iled
    0.17
    aps
    0.17
    apy
    0.17
    ley
    0.16
     dass
    0.15
    oth
    0.15
     sánh
    0.15
    ars
    0.15
    Activations Density 0.018%

    No Known Activations