© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37841
    Prev
    Next
    INDEX
    Explanations

    central sulphide zones

    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
     Flint
    -0.11
     Oil
    -0.10
    åĪ¶éĢł
    -0.10
     petroleum
    -0.09
     Drew
    -0.09
     Manning
    -0.09
     gran
    -0.09
    åĪ·
    -0.09
     Petroleum
    -0.09
     Cros
    -0.08
    POSITIVE LOGITS
     mine
    0.22
     tail
    0.20
     ore
    0.20
     gold
    0.19
     heap
    0.18
     Mine
    0.17
     fro
    0.16
    Mine
    0.16
    gold
    0.16
     cyan
    0.16
    Activations Density 0.056%

    No Known Activations