© 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. 35563
    Prev
    Next
    INDEX
    Explanations

    do anything

    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
    ewan
    -0.10
     unarmed
    -0.10
    amer
    -0.09
     unreal
    -0.09
    onet
    -0.09
    íİĺ
    -0.09
    akat
    -0.09
    'gc
    -0.09
     DERP
    -0.09
    ä¸į足
    -0.08
    POSITIVE LOGITS
     free
    0.24
     fre
    0.23
    èĩªçĶ±
    0.21
     freedom
    0.20
    free
    0.18
     Ñģвоб
    0.17
     آزاد
    0.17
     Ñģвобод
    0.17
     Freedom
    0.16
    fre
    0.16
    Activations Density 0.075%

    No Known Activations