© 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. 57856
    Prev
    Next
    INDEX
    Explanations

    against the wall or tree

    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
    •FOX

    No Comments

    Negative Logits
     roads
    -0.10
    enci
    -0.10
     sidewalks
    -0.10
    åłĤ
    -0.10
     Roads
    -0.10
    Deck
    -0.09
     sidewalk
    -0.09
     Roof
    -0.09
    WG
    -0.09
     tongue
    -0.09
    POSITIVE LOGITS
     wall
    0.27
     walls
    0.19
    wall
    0.18
    å¢Ļ
    0.17
     trees
    0.16
     WALL
    0.16
     tree
    0.16
     tÆ°á»Ŀng
    0.15
    Wall
    0.15
    æŁ±
    0.14
    Activations Density 0.051%

    No Known Activations