© 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. 49329
    Prev
    Next
    INDEX
    Explanations

    path ahead

    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
     prior
    -0.12
     Prior
    -0.11
     pre
    -0.10
    ussen
    -0.09
     throughout
    -0.09
    _Pre
    -0.09
    zug
    -0.08
    ilig
    -0.08
     Previous
    -0.08
     prep
    -0.08
    POSITIVE LOGITS
     ahead
    0.86
     Ahead
    0.70
    ahead
    0.66
    Ahead
    0.66
    -ahead
    0.50
     впеÑĢед
    0.44
     devant
    0.23
     adel
    0.20
    åīį
    0.19
     ìķŀ
    0.18
    Activations Density 0.076%

    No Known Activations