© 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. 44323
    Prev
    Next
    INDEX
    Explanations

    parents and family members

    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
    å§Ĭ
    -0.10
    æĹ
    -0.10
    夫人
    -0.10
    åıĶ
    -0.09
    AppState
    -0.09
    erton
    -0.09
    家æĹı
    -0.09
    å°ij女
    -0.09
    peg
    -0.09
    enton
    -0.09
    POSITIVE LOGITS
     adopt
    0.12
     biological
    0.11
    ÏĦÎŃÏģα
    0.10
    chter
    0.10
     foster
    0.10
     Foster
    0.10
    uter
    0.10
    anager
    0.09
    à¸Ĭาย
    0.09
     parents
    0.09
    Activations Density 0.132%

    No Known Activations