© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38827
    Prev
    Next
    INDEX
    Explanations

    attention mechanism and heads

    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
    gers
    -0.10
    icher
    -0.10
    ries
    -0.10
    usc
    -0.09
    urch
    -0.09
    wards
    -0.09
    utt
    -0.09
    PTY
    -0.09
    wis
    -0.09
    çĻ
    -0.09
    POSITIVE LOGITS
    al
    0.24
     span
    0.19
     paid
    0.18
    -gr
    0.16
     deficit
    0.14
     Paid
    0.14
     detail
    0.14
    -get
    0.13
     attention
    0.13
     spans
    0.13
    Activations Density 0.015%

    No Known Activations