© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38624
    Prev
    Next
    INDEX
    Explanations

    acids and car compounds

    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
     ar
    -0.11
     Giang
    -0.10
     arz
    -0.10
     stil
    -0.10
     pur
    -0.10
     Banc
    -0.09
    zas
    -0.09
    .calls
    -0.09
     arom
    -0.09
    æ´¥
    -0.09
    POSITIVE LOGITS
     tart
    0.16
     succ
    0.15
     Succ
    0.14
     acids
    0.13
     Tart
    0.13
     cit
    0.13
     carn
    0.13
     rac
    0.12
     est
    0.12
     acrylic
    0.12
    Activations Density 0.179%

    No Known Activations