© 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. 37562
    Prev
    Next
    INDEX
    Explanations

    asking, seeking, or needing

    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
    uckets
    -0.09
    галÑĸ
    -0.09
    cies
    -0.09
     MMI
    -0.08
    ALER
    -0.08
    726
    -0.08
     Demir
    -0.08
    ichage
    -0.08
    ãģ¾ãģ¾
    -0.08
    ict
    -0.08
    POSITIVE LOGITS
     looking
    0.29
    looking
    0.25
     Looking
    0.24
    Looking
    0.23
     seek
    0.21
     seeking
    0.20
     seeks
    0.19
    -looking
    0.18
     hled
    0.16
     sought
    0.16
    Activations Density 0.046%

    No Known Activations