© 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. 34003
    Prev
    Next
    INDEX
    Explanations

    family

    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
     friendship
    -0.18
     Friendship
    -0.17
     friendships
    -0.13
    Friend
    -0.11
     FRIEND
    -0.10
     duo
    -0.10
     classes
    -0.10
    两人
    -0.10
    åıĭ
    -0.10
    friend
    -0.09
    POSITIVE LOGITS
     family
    0.36
    family
    0.28
     Family
    0.26
     patriarch
    0.26
    Family
    0.24
    -family
    0.22
    家æĹı
    0.21
     FAMILY
    0.21
    amily
    0.21
    .family
    0.20
    Activations Density 0.150%

    No Known Activations