© 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. 795
    Prev
    Next
    INDEX
    Explanations

    purposeful actions after "to"

    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
    EMPLARY
    -0.10
    oze
    -0.09
    Latch
    -0.09
    stead
    -0.09
    umbs
    -0.09
    oret
    -0.09
    thon
    -0.08
    žel
    -0.08
    eca
    -0.08
    oders
    -0.08
    POSITIVE LOGITS
     help
    0.16
    -date
    0.16
    ting
    0.15
     rival
    0.15
    iling
    0.15
     enable
    0.14
     aid
    0.14
    asting
    0.13
    tes
    0.13
     boot
    0.13
    Activations Density 0.095%

    No Known Activations