© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1321
    Prev
    Next
    INDEX
    Explanations

    self- or high- prefix

    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
    ientos
    -0.09
     Damen
    -0.09
    .esp
    -0.09
    tej
    -0.09
    rapper
    -0.08
    forces
    -0.08
     rigor
    -0.08
    enerator
    -0.08
    orld
    -0.08
     convers
    -0.08
    POSITIVE LOGITS
    etre
    0.11
     è¾
    0.09
    sie
    0.08
    åĬłå·¥
    0.08
     Bew
    0.08
    antal
    0.08
    samp
    0.08
    ug
    0.08
     Raum
    0.08
    tems
    0.08
    Activations Density 0.108%

    No Known Activations