© 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. 8695
    Prev
    Next
    INDEX
    Explanations

    online gaming terms

    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
     Dungeons
    -0.11
     fan
    -0.10
    ucha
    -0.10
     RPG
    -0.09
     íĮ¬
    -0.09
     Burl
    -0.09
     jadx
    -0.09
    ering
    -0.09
     fucks
    -0.09
    Universal
    -0.08
    POSITIVE LOGITS
     lag
    0.16
     frag
    0.14
     skill
    0.14
     toxic
    0.13
     salty
    0.13
     lobby
    0.12
     AF
    0.12
     skilled
    0.12
    skill
    0.12
    Skill
    0.12
    Activations Density 0.071%

    No Known Activations