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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43910
    Prev
    Next
    INDEX
    Explanations

    explicitly stated or found concepts

    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
     Gon
    -0.09
    tz
    -0.09
    411
    -0.09
    reib
    -0.08
     Schn
    -0.08
     comple
    -0.08
    icular
    -0.08
     fo
    -0.08
    alle
    -0.08
     Elevated
    -0.08
    POSITIVE LOGITS
     stated
    0.11
    /exp
    0.10
     rõ
    0.09
    andra
    0.09
     flav
    0.08
    ²
    0.08
     stating
    0.08
    YES
    0.08
     Hedge
    0.08
    æĺİ
    0.08
    Activations Density 0.009%

    No Known Activations