© 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. 18195
    Prev
    Next
    INDEX
    Explanations

    latter, former, or later

    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
     丶
    -0.09
    âĶ£
    -0.09
    aida
    -0.08
    ooter
    -0.08
    onte
    -0.08
    ytt
    -0.08
    uce
    -0.08
    práv
    -0.08
    ocale
    -0.08
    inder
    -0.08
    POSITIVE LOGITS
     latter
    1.58
     Latter
    0.78
     اÙĦأخ
    0.34
     former
    0.29
     letz
    0.28
     поÑģлед
    0.27
     later
    0.21
    former
    0.21
    ãģĵãģ¡ãĤī
    0.20
     laat
    0.20
    Activations Density 0.174%

    No Known Activations