© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45309
    Prev
    Next
    INDEX
    Explanations

    creating, generating, and providing

    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
    ëį°
    -0.12
     gì
    -0.08
     everything
    -0.08
    898
    -0.08
     Baron
    -0.08
    /big
    -0.08
    ige
    -0.08
    onde
    -0.08
    ability
    -0.08
     Sher
    -0.08
    POSITIVE LOGITS
    /testing
    0.14
    /respond
    0.13
    /logging
    0.13
     certain
    0.13
    /loading
    0.10
    /exec
    0.10
    æŁIJ
    0.10
    redients
    0.10
    /upload
    0.10
     ë¸
    0.10
    Activations Density 0.115%

    No Known Activations