© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23999
    Prev
    Next
    INDEX
    Explanations

    Proxmox VE enterprise community

    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
    arial
    -0.10
    acle
    -0.09
    .spy
    -0.09
     Loot
    -0.09
    -debug
    -0.09
    ACLE
    -0.09
     exploit
    -0.09
     FTP
    -0.09
    adies
    -0.08
     oracle
    -0.08
    POSITIVE LOGITS
     HA
    0.13
     enterprise
    0.13
     community
    0.13
     Community
    0.12
     Enterprise
    0.12
     open
    0.12
     ext
    0.12
     pl
    0.11
     dec
    0.11
    community
    0.11
    Activations Density 0.102%

    No Known Activations