© 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. 23814
    Prev
    Next
    INDEX
    Explanations

    troll posts and their quantity

    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
     slander
    -0.11
     cocks
    -0.09
    ande
    -0.08
    goog
    -0.08
     bias
    -0.08
     bench
    -0.08
     Consent
    -0.08
     tạp
    -0.08
     Carm
    -0.08
     charging
    -0.08
    POSITIVE LOGITS
     sock
    0.12
     canned
    0.12
     flame
    0.11
    sock
    0.11
     online
    0.11
     troll
    0.11
     thread
    0.11
     flaming
    0.11
     Online
    0.11
     posts
    0.11
    Activations Density 0.083%

    No Known Activations