© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41720
    Prev
    Next
    INDEX
    Explanations

    driving Pacific

    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
    walking
    -0.14
    æŃ©
    -0.14
     walk
    -0.13
     walkers
    -0.13
     sidewalk
    -0.13
     walking
    -0.12
    walk
    -0.12
     walked
    -0.12
    Walking
    -0.12
     sidewalks
    -0.12
    POSITIVE LOGITS
     drive
    0.33
     driving
    0.32
     drives
    0.28
     road
    0.27
     Drive
    0.27
     Driving
    0.25
     drove
    0.24
    drive
    0.24
    Driving
    0.23
    -driving
    0.23
    Activations Density 0.084%

    No Known Activations