© 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. 36277
    Prev
    Next
    INDEX
    Explanations

    feelings and states of being

    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
    eld
    -0.09
    ukan
    -0.09
    inou
    -0.09
     СÑĤа
    -0.09
    rup
    -0.09
     Dank
    -0.08
    æĤ£
    -0.08
    åŁĭ
    -0.08
    دÛĮد
    -0.08
     æ®
    -0.08
    POSITIVE LOGITS
     comfortable
    0.47
     ease
    0.45
    comfort
    0.36
     Comfort
    0.35
     comfort
    0.35
    Comfort
    0.34
     Ease
    0.34
    ease
    0.33
    Ease
    0.31
     thoải
    0.30
    Activations Density 0.064%

    No Known Activations