© 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. 25499
    Prev
    Next
    INDEX
    Explanations

    absence gone leave bare

    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
     dÃ¼ÅŁÃ¼r
    -0.10
    åºŁ
    -0.10
     ç±
    -0.09
    indow
    -0.09
    izmet
    -0.09
    .persistent
    -0.09
     ÑģмеÑĢÑĤÑĮ
    -0.08
    ä½Ļ
    -0.08
    ç±į
    -0.08
    218
    -0.08
    POSITIVE LOGITS
     gone
    0.72
     Gone
    0.61
    gone
    0.58
     absence
    0.22
     gon
    0.20
    .GONE
    0.19
     went
    0.18
    åİ»
    0.18
    åİ»äºĨ
    0.16
     åİ
    0.15
    Activations Density 0.060%

    No Known Activations