© 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. 43353
    Prev
    Next
    INDEX
    Explanations

    introducing lists and examples

    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
    534
    -0.09
     proport
    -0.09
     Playboy
    -0.08
    /OR
    -0.08
    703
    -0.08
    符åIJĪ
    -0.08
     Hun
    -0.08
     Nej
    -0.08
     ï¼¼:
    -0.08
     Brent
    -0.08
    POSITIVE LOGITS
     including
    0.21
    以åıĬ
    0.19
    åıĬåħ¶
    0.18
    including
    0.17
     how
    0.17
     its
    0.16
     Including
    0.15
    its
    0.15
     their
    0.14
    how
    0.14
    Activations Density 0.133%

    No Known Activations