© 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. 33392
    Prev
    Next
    INDEX
    Explanations

    familiarity and expertise

    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
    oad
    -0.11
     diligent
    -0.10
    ool
    -0.09
     incompetent
    -0.09
     knack
    -0.09
     onwards
    -0.09
    esson
    -0.09
     incompet
    -0.09
     newbie
    -0.09
     ridge
    -0.09
    POSITIVE LOGITS
     familiar
    0.28
     vers
    0.26
     convers
    0.25
    versed
    0.23
     experts
    0.23
    çĨŁ
    0.22
     comfortable
    0.21
    amiliar
    0.21
     Fam
    0.20
     able
    0.20
    Activations Density 0.156%

    No Known Activations