© 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. 47053
    Prev
    Next
    INDEX
    Explanations

    breakdown, decay, degradation, hydrolysis

    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
     discontin
    -0.10
     Gat
    -0.09
     глÑĥ
    -0.08
     Karlov
    -0.08
    ersions
    -0.08
     cyclic
    -0.08
    ırak
    -0.08
    rides
    -0.08
    forc
    -0.08
     Mist
    -0.08
    POSITIVE LOGITS
     breakdown
    0.31
     decay
    0.25
     decomposition
    0.25
     decom
    0.21
    decay
    0.21
     rot
    0.19
     Decom
    0.18
    Deg
    0.18
    _decay
    0.18
     degradation
    0.17
    Activations Density 0.106%

    No Known Activations