© 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. 10192
    Prev
    Next
    INDEX
    Explanations

    complete the following sentence or story

    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
    oya
    -0.10
    ãĢĢï½Į
    -0.09
     Boeh
    -0.09
    inated
    -0.08
     ï½Į
    -0.08
     ãĥ¼
    -0.08
    _APPRO
    -0.08
    ONTAL
    -0.08
    _RPC
    -0.08
    ä¸Ģåį·
    -0.08
    POSITIVE LOGITS
     incomplete
    0.23
     unfinished
    0.23
     sentence
    0.21
     sentences
    0.19
     completion
    0.19
     completing
    0.18
     completed
    0.17
    unfinished
    0.17
    Incomplete
    0.17
     missing
    0.17
    Activations Density 0.090%

    No Known Activations