© 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. 56702
    Prev
    Next
    INDEX
    Explanations

    information data contributions images

    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
    æ¸
    -0.10
    ared
    -0.09
    apiro
    -0.09
    poss
    -0.08
    avatel
    -0.08
     Berger
    -0.08
    hta
    -0.08
    SBATCH
    -0.08
    krv
    -0.08
    ByText
    -0.08
    POSITIVE LOGITS
     information
    0.26
    æĿ¥èĩª
    0.20
     contents
    0.18
     material
    0.17
    information
    0.17
     content
    0.17
     contributions
    0.17
     insights
    0.16
     data
    0.16
     info
    0.15
    Activations Density 0.253%

    No Known Activations