© 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. 23935
    Prev
    Next
    INDEX
    Explanations

    get lost or arrived

    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
    Ob
    -0.09
     ká»
    -0.09
     dom
    -0.09
    istant
    -0.09
     Carm
    -0.08
     Shock
    -0.08
    azzi
    -0.08
     Wilkinson
    -0.08
     Hin
    -0.08
     Gain
    -0.08
    POSITIVE LOGITS
     lost
    0.38
     Lost
    0.32
    lost
    0.30
    è¿·
    0.30
    Lost
    0.30
     gets
    0.25
     perder
    0.25
     getting
    0.25
     perd
    0.24
     поÑĤеÑĢ
    0.24
    Activations Density 0.092%

    No Known Activations