© 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. 34913
    Prev
    Next
    INDEX
    Explanations

    Go package and imports

    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
    íĥģ
    -0.10
     hus
    -0.09
    ogan
    -0.09
    arkin
    -0.09
    airy
    -0.08
    jsonwebtoken
    -0.08
    GROUND
    -0.08
    .jar
    -0.08
    illis
    -0.08
    @Getter
    -0.08
    POSITIVE LOGITS
     func
    0.26
    func
    0.26
    .go
    0.20
     Go
    0.18
     package
    0.17
    .func
    0.16
     main
    0.15
     go
    0.15
    Go
    0.14
    (func
    0.14
    Activations Density 0.024%

    No Known Activations