© 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. 16729
    Prev
    Next
    INDEX
    Explanations

    Tumbleweed snapshot software updates

    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
     Rab
    -0.11
     Bean
    -0.09
    uele
    -0.08
    odia
    -0.08
    .sess
    -0.08
     indiv
    -0.08
    needle
    -0.08
     handshake
    -0.08
    AREST
    -0.08
    Bean
    -0.08
    POSITIVE LOGITS
     Flake
    0.15
     pk
    0.13
     flakes
    0.13
    pk
    0.13
    flake
    0.12
    drv
    0.12
    Pk
    0.11
     fl
    0.11
    å¢
    0.11
     n
    0.10
    Activations Density 0.014%

    No Known Activations