© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 17710
    Prev
    Next
    INDEX
    Explanations

    reserved and quiet demeanor

    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
     timid
    -0.11
     sly
    -0.10
     Gerr
    -0.09
    duk
    -0.09
    reck
    -0.09
     vivid
    -0.09
     nim
    -0.09
    _bold
    -0.08
     innoc
    -0.08
     porous
    -0.08
    POSITIVE LOGITS
     cool
    0.26
     sto
    0.26
     reserved
    0.24
     reserve
    0.22
     Sto
    0.22
     Reserved
    0.21
    cool
    0.20
     Cool
    0.20
     calm
    0.20
     poker
    0.20
    Activations Density 0.142%

    No Known Activations