© 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. 45082
    Prev
    Next
    INDEX
    Explanations

    maze and path generation

    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
     CASCADE
    -0.11
     cascade
    -0.11
     casc
    -0.10
     wrest
    -0.10
     Sherlock
    -0.10
    cascade
    -0.09
    riangle
    -0.09
    _sphere
    -0.09
    edList
    -0.09
     Timeline
    -0.09
    POSITIVE LOGITS
    è¿·
    0.19
     maze
    0.18
    maze
    0.18
     walls
    0.16
     Maze
    0.15
     path
    0.15
     wall
    0.14
    maz
    0.14
     exit
    0.13
     labyrinth
    0.12
    Activations Density 0.049%

    No Known Activations