© 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. 41812
    Prev
    Next
    INDEX
    Explanations

    diamonds are found

    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
     platinum
    -0.11
     gold
    -0.11
     jewels
    -0.11
     Diamonds
    -0.10
     Diamond
    -0.10
     Shelf
    -0.10
     Leer
    -0.10
     Stainless
    -0.10
     diamonds
    -0.10
     bronze
    -0.10
    POSITIVE LOGITS
     peg
    0.15
     hardness
    0.14
     streak
    0.13
    inite
    0.13
    osite
    0.11
     cle
    0.11
    ethyst
    0.11
     adul
    0.11
    prite
    0.11
     Moh
    0.11
    Activations Density 0.023%

    No Known Activations