© 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. 55630
    Prev
    Next
    INDEX
    Explanations

    research and development

    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
    -and
    -0.10
     fetisch
    -0.09
    995
    -0.09
     oder
    -0.09
    âĶĤ
    -0.09
     lecken
    -0.09
     bzw
    -0.08
    à¹ģละส
    -0.08
    yg
    -0.08
     und
    -0.08
    POSITIVE LOGITS
    以åıĬ
    0.35
    ï¼Į以åıĬ
    0.35
     serta
    0.34
     oraz
    0.29
     sowie
    0.27
     ê·¸ë¦¬ê³ł
    0.25
     plus
    0.22
     samt
    0.21
     तथ
    0.21
     ainsi
    0.19
    Activations Density 0.263%

    No Known Activations