© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18374
    Prev
    Next
    INDEX
    Explanations

    this is/these are

    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
    ovel
    -0.09
    aepernick
    -0.08
    und
    -0.08
    unsch
    -0.08
    çĮ
    -0.08
    obra
    -0.08
    atto
    -0.08
    ÙĦÙĦ
    -0.08
    #__
    -0.08
    AspNet
    -0.08
    POSITIVE LOGITS
    åıªæĺ¯
    0.21
    æĺ¯ä¸Ģ个
    0.19
    æĺ¯ä¸Ģ
    0.17
     particular
    0.15
     just
    0.13
     exact
    0.13
     yalnızca
    0.13
     is
    0.13
     sadece
    0.12
     adalah
    0.12
    Activations Density 0.028%

    No Known Activations