© 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. 13415
    Prev
    Next
    INDEX
    Explanations

    known for their soft

    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
    HIR
    -0.10
     Swe
    -0.09
    IMS
    -0.09
     Mist
    -0.09
    ymb
    -0.09
     supporting
    -0.08
    empt
    -0.08
     Crescent
    -0.08
     çķ
    -0.08
     timed
    -0.08
    POSITIVE LOGITS
     difficult
    0.38
    éļ¾
    0.33
    éĽ£
    0.33
    Stub
    0.31
     difÃŃcil
    0.29
     Stub
    0.29
     khó
    0.29
     ÑĤÑĢÑĥд
    0.29
     diffic
    0.29
     difficile
    0.28
    Activations Density 0.186%

    No Known Activations