© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    contrast conjunctions and non-English words

    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
    irs
    -0.09
     dedi
    -0.08
     naopak
    -0.08
    adora
    -0.08
     Butler
    -0.08
     öyle
    -0.08
    ždy
    -0.08
    ãģłãģĭãĤī
    -0.08
    HOOK
    -0.08
    butt
    -0.08
    POSITIVE LOGITS
    ï¼Įä½Ĩ
    0.18
     but
    0.16
     BUT
    0.15
     mais
    0.14
     nhÆ°ng
    0.14
    ï¼Įä½Ĩæĺ¯
    0.14
     αλλά
    0.14
     à¹ģà¸ķ
    0.14
    ãģłãģĮ
    0.14
     However
    0.14
    Activations Density 0.283%

    No Known Activations