© 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. 63621
    Prev
    Next
    INDEX
    Explanations

    recovery and recuperation

    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
     reunited
    -0.12
    Reuse
    -0.11
     reconc
    -0.10
    874
    -0.10
    haus
    -0.09
     Renew
    -0.09
     reinst
    -0.09
    oại
    -0.09
    (reinterpret
    -0.09
     å¾Ĵ
    -0.09
    POSITIVE LOGITS
     recovery
    0.59
     recover
    0.52
     Recovery
    0.46
     recovered
    0.43
     recovering
    0.40
    recover
    0.39
    _recovery
    0.36
     Recover
    0.35
    covery
    0.31
     récup
    0.29
    Activations Density 0.091%

    No Known Activations