© 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. 56318
    Prev
    Next
    INDEX
    Explanations

    user actions and input

    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
    vido
    -0.09
    èĴ
    -0.09
     KN
    -0.09
    çĿ
    -0.09
    795
    -0.09
     tane
    -0.08
     Cush
    -0.08
     Edmund
    -0.08
     Kling
    -0.08
     Neville
    -0.08
    POSITIVE LOGITS
     input
    0.20
    input
    0.18
    -input
    0.16
    _input
    0.15
    è¾ĵåħ¥
    0.14
     Input
    0.14
    Input
    0.14
    land
    0.13
     inputs
    0.13
     ввод
    0.12
    Activations Density 0.057%

    No Known Activations