© 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. 60339
    Prev
    Next
    INDEX
    Explanations

    remaining five

    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
    22
    -0.10
    彡
    -0.09
    EQ
    -0.09
    âij¡
    -0.09
     Latter
    -0.08
    82
    -0.08
    åįģåħ«
    -0.08
    02
    -0.08
    -eight
    -0.08
    62
    -0.08
    POSITIVE LOGITS
     fifth
    0.33
     Fifth
    0.28
    5
    0.28
     five
    0.25
     пÑıÑĤ
    0.24
    ï¼ķ
    0.22
    äºĶ
    0.22
     beÅŁ
    0.22
    -five
    0.22
     fün
    0.21
    Activations Density 0.069%

    No Known Activations