© 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. 62359
    Prev
    Next
    INDEX
    Explanations

    process steps and stages

    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
     cour
    -0.09
    arus
    -0.09
    /respond
    -0.09
    edBy
    -0.09
     impass
    -0.09
     fallen
    -0.09
    indr
    -0.08
    iek
    -0.08
    ichel
    -0.08
    igs
    -0.08
    POSITIVE LOGITS
     stage
    0.16
     step
    0.16
     phase
    0.12
    step
    0.11
     followed
    0.11
    stage
    0.10
    ment
    0.10
     process
    0.09
    à¹ģละà¸ģาร
    0.09
    ï¾Ł
    0.09
    Activations Density 0.039%

    No Known Activations