© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 37777
    Prev
    Next
    INDEX
    Explanations

    staying in places

    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
    ãģĬãĤĬ
    -0.14
    ãģĦãģ¾ãģĻ
    -0.10
    izable
    -0.10
    roker
    -0.10
     inde
    -0.09
    loh
    -0.09
    645
    -0.09
    nÄĽji
    -0.09
    akin
    -0.09
    etur
    -0.09
    POSITIVE LOGITS
    cation
    0.19
     put
    0.13
    athom
    0.13
     away
    0.12
     true
    0.12
     busy
    0.11
     PUT
    0.10
    ders
    0.10
    away
    0.10
    ÑģÑı
    0.10
    Activations Density 0.016%

    No Known Activations