Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44920
    Prev
    Next
    INDEX
    Explanations

    switch and transition

    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
     reloc
    -0.11
    èŃľ
    -0.10
     relocated
    -0.09
    è°±
    -0.09
     Shuffle
    -0.09
    alama
    -0.09
    mob
    -0.09
     Carousel
    -0.09
     relocation
    -0.08
     Mobility
    -0.08
    POSITIVE LOGITS
     switch
    0.36
     transition
    0.30
    switch
    0.29
     shift
    0.29
     Switch
    0.26
     switching
    0.26
    Switch
    0.25
    \tswitch
    0.25
    -switch
    0.24
     switched
    0.24
    Activations Density 0.117%

    No Known Activations