© 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. 51753
    Prev
    Next
    INDEX
    Explanations

    NAT outbound rules allow bypass

    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
    izzo
    -0.10
    vell
    -0.10
     liá»ģn
    -0.09
    Adjacent
    -0.09
    äs
    -0.09
     Kes
    -0.09
    ï¼ł
    -0.08
     suff
    -0.08
    .ReadAll
    -0.08
    .IsNullOr
    -0.08
    POSITIVE LOGITS
     tunnel
    0.21
     Nat
    0.21
     NAT
    0.21
    Nat
    0.20
     tunnels
    0.20
     nat
    0.19
    nat
    0.18
     Tunnel
    0.17
     tun
    0.17
    ç©¿
    0.14
    Activations Density 0.073%

    No Known Activations