© 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. 50827
    Prev
    Next
    INDEX
    Explanations

    entering, into, about, in

    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
     him
    -0.17
    him
    -0.11
     whom
    -0.11
     oneself
    -0.10
     us
    -0.10
    us
    -0.10
     æ´
    -0.09
     yourself
    -0.09
     Persons
    -0.08
    archives
    -0.08
    POSITIVE LOGITS
    人çļĦ
    0.27
     peoples
    0.24
     ÑĩÑĥж
    0.23
    èĢħçļĦ
    0.19
     ano
    0.19
    人们
    0.18
    人ãģ®
    0.18
     someone
    0.17
    mens
    0.16
     womens
    0.16
    Activations Density 0.226%

    No Known Activations