© 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. 23765
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun "their"

    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
     hers
    -0.20
     ours
    -0.18
     yours
    -0.15
     onu
    -0.11
     YOUR
    -0.10
    å®ĥ
    -0.10
    Ìĥ
    -0.09
     itself
    -0.08
     à¤Ĩपà¤ķ
    -0.08
     à¤īसन
    -0.08
    POSITIVE LOGITS
     their
    0.71
    their
    0.57
     Their
    0.51
    Their
    0.50
     иÑħ
    0.47
     ihre
    0.47
     loro
    0.44
     jejich
    0.43
     leurs
    0.42
     leur
    0.41
    Activations Density 0.336%

    No Known Activations