© 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. 37116
    Prev
    Next
    INDEX
    Explanations

    potentially negative outcomes

    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
     likely
    -0.11
    azy
    -0.11
    мовÑĸÑĢ
    -0.09
     potential
    -0.09
    owitz
    -0.09
     поÑĤен
    -0.09
     Likely
    -0.09
    ãĤĪãģı
    -0.08
    gos
    -0.08
    olley
    -0.08
    POSITIVE LOGITS
    /pro
    0.18
    ities
    0.18
    ity
    0.18
    mente
    0.16
    weise
    0.12
     sogar
    0.11
     even
    0.11
    l
    0.11
    /current
    0.11
    ties
    0.10
    Activations Density 0.019%

    No Known Activations