© 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. 63250
    Prev
    Next
    INDEX
    Explanations

    explain or help

    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
     завиÑģим
    -0.09
    hawks
    -0.09
     scaleX
    -0.09
     yans
    -0.09
     ÑģоÑħÑĢа
    -0.08
    pei
    -0.08
    ãĤ
    -0.08
     Belly
    -0.08
    Hints
    -0.08
    ButtonText
    -0.08
    POSITIVE LOGITS
     explain
    0.61
     explained
    0.59
     explains
    0.55
     explanation
    0.53
     explaining
    0.48
    explained
    0.48
     explanations
    0.47
    explain
    0.46
     обÑĬÑıÑģ
    0.46
     erklä
    0.44
    Activations Density 0.311%

    No Known Activations