© 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. 17762
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and entities

    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
    éĥ½ä¼ļ
    -0.10
    inati
    -0.10
    èĪį
    -0.09
    uky
    -0.09
    ä¹Łæľī
    -0.09
    mamak
    -0.09
     resil
    -0.09
     none
    -0.09
    ãĤ«ãĥ«
    -0.09
     Lazar
    -0.09
    POSITIVE LOGITS
     cannot
    0.16
    æĺ¯ä¸į
    0.13
     isn
    0.12
    cannot
    0.12
     pale
    0.12
     remain
    0.11
     remains
    0.11
    sim
    0.11
     fails
    0.10
     doesn
    0.10
    Activations Density 0.139%

    No Known Activations