© 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. 44043
    Prev
    Next
    INDEX
    Explanations

    reactions and shifts in attention

    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
    printStats
    -0.11
    .createFrom
    -0.10
    콩
    -0.10
     å¾Ĵ
    -0.09
     niên
    -0.09
     tob
    -0.09
     retention
    -0.09
    çĦ¦
    -0.09
    åŁ
    -0.09
    isha
    -0.09
    POSITIVE LOGITS
     reply
    0.17
     speech
    0.17
     surprise
    0.16
     shock
    0.16
     silence
    0.15
     digest
    0.14
     replied
    0.14
     mul
    0.14
     response
    0.14
    èĢĥèĻij
    0.13
    Activations Density 0.038%

    No Known Activations