© 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. 27043
    Prev
    Next
    INDEX
    Explanations

    difficult, limited, or caught

    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
     sidelined
    -0.14
     Suppress
    -0.11
     obscured
    -0.11
    utr
    -0.10
     saturated
    -0.10
     flooded
    -0.10
     obsc
    -0.10
     depleted
    -0.10
    uito
    -0.10
     crippled
    -0.10
    POSITIVE LOGITS
     ham
    0.31
    ham
    0.26
     hinder
    0.21
     mar
    0.20
    Ham
    0.19
     Ham
    0.18
     limited
    0.18
    indered
    0.18
     handic
    0.18
     Hindered
    0.17
    Activations Density 0.093%

    No Known Activations