© 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. 14330
    Prev
    Next
    INDEX
    Explanations

    cell size or variable declarations

    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
     Wings
    -0.10
     Roots
    -0.10
     wings
    -0.10
     Brend
    -0.10
     seizing
    -0.09
     dotted
    -0.09
     winters
    -0.09
     Vanderbilt
    -0.09
    isRequired
    -0.09
    }elseif
    -0.09
    POSITIVE LOGITS
    .setCellValue
    0.12
     cell
    0.12
     grass
    0.11
     Cell
    0.11
     cells
    0.11
     walls
    0.10
    èįī
    0.10
     empty
    0.10
     Empty
    0.10
     EMPTY
    0.10
    Activations Density 0.073%

    No Known Activations