© 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. 40774
    Prev
    Next
    INDEX
    Explanations

    to merge

    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
     Sampler
    -0.09
     Ser
    -0.08
    CRY
    -0.08
     Marketplace
    -0.08
     MIX
    -0.08
     Sophia
    -0.08
     mixed
    -0.08
    RITE
    -0.08
    rud
    -0.08
    umed
    -0.08
    POSITIVE LOGITS
     merger
    0.30
     merge
    0.29
    .merge
    0.28
    merge
    0.28
    åIJĪ
    0.28
     merg
    0.28
     Merge
    0.26
    Merge
    0.25
     Mer
    0.24
     åIJĪ
    0.24
    Activations Density 0.081%

    No Known Activations