© 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. 35801
    Prev
    Next
    INDEX
    Explanations

    smells good

    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
     tasting
    -0.10
    788
    -0.10
     Dess
    -0.10
     sandwich
    -0.10
     Sandwich
    -0.09
     Hind
    -0.09
     dessert
    -0.08
    allis
    -0.08
     tasted
    -0.08
    uta
    -0.08
    POSITIVE LOGITS
     aroma
    0.21
     arom
    0.21
     smells
    0.21
     wa
    0.20
    é¦Ļ
    0.19
     запаÑħ
    0.19
     smell
    0.16
     scent
    0.15
    éĹ»
    0.15
     od
    0.15
    Activations Density 0.039%

    No Known Activations