© 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. 18351
    Prev
    Next
    INDEX
    Explanations

    smell of feces or embarrassment

    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
     saliva
    -0.11
     drip
    -0.10
     bone
    -0.10
    anki
    -0.10
     parking
    -0.09
     rubble
    -0.09
    iyon
    -0.09
    kaar
    -0.09
     Gins
    -0.09
     Fam
    -0.09
    POSITIVE LOGITS
     gross
    0.26
     Gross
    0.24
    gross
    0.21
    èĩ
    0.18
     grosse
    0.17
     запаÑħ
    0.16
     odor
    0.16
     gag
    0.16
     smell
    0.15
     fec
    0.15
    Activations Density 0.102%

    No Known Activations