© 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. 164
    Prev
    Next
    INDEX
    Explanations

    believe that

    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
    quam
    -0.10
    loo
    -0.09
     loop
    -0.09
    iter
    -0.09
    ogan
    -0.08
    âĶģ
    -0.08
    Loop
    -0.08
    ppt
    -0.08
    asser
    -0.08
    اپ
    -0.08
    POSITIVE LOGITS
     rằng
    0.19
     bahwa
    0.18
     believes
    0.15
     believe
    0.14
    -bel
    0.12
     believed
    0.12
     дека
    0.12
    çĽ¸ä¿¡
    0.12
     that
    0.12
     že
    0.11
    Activations Density 0.014%

    No Known Activations