© 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. 30307
    Prev
    Next
    INDEX
    Explanations

    suitable donor, continue plan

    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
    à¸Ľà¸£
    -0.10
    ä¿®
    -0.09
     gyro
    -0.09
     rede
    -0.09
     Enemies
    -0.08
     vap
    -0.08
    ihu
    -0.08
     foes
    -0.08
     voc
    -0.08
    peed
    -0.08
    POSITIVE LOGITS
     victim
    0.15
     accomp
    0.13
     victims
    0.13
     Victims
    0.13
    å®ŀæĸ½
    0.12
     perpet
    0.12
     targets
    0.12
     plan
    0.12
     getaway
    0.11
     Targets
    0.11
    Activations Density 0.182%

    No Known Activations