© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35188
    Prev
    Next
    INDEX
    Explanations

    steps to prepare

    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
     precedent
    -0.10
     precedence
    -0.10
     preced
    -0.09
     Keller
    -0.09
    lrt
    -0.09
    Pending
    -0.08
    opa
    -0.08
    ï¾Ł
    -0.08
    pending
    -0.08
     pending
    -0.08
    POSITIVE LOGITS
     preparation
    0.67
     prepare
    0.58
     prepared
    0.58
     Preparation
    0.56
     preparations
    0.54
    åĩĨå¤ĩ
    0.52
     подгоÑĤов
    0.52
    prepared
    0.50
     preparing
    0.50
     Prepare
    0.49
    Activations Density 0.137%

    No Known Activations