© 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. 24887
    Prev
    Next
    INDEX
    Explanations

    end of document marker

    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
     Pest
    -0.09
    alion
    -0.09
    IRTH
    -0.09
     Py
    -0.08
    vious
    -0.08
     Tribal
    -0.08
     egregious
    -0.08
    -âĢIJ
    -0.08
     Crisis
    -0.08
    routeParams
    -0.07
    POSITIVE LOGITS
     diplomacy
    0.09
    ohana
    0.08
    ederation
    0.08
    ormsg
    0.08
    å°½
    0.08
    ULO
    0.08
     Kear
    0.08
    æĹ
    0.08
     pan
    0.07
    VML
    0.07
    Activations Density 0.418%

    No Known Activations