© 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. 23724
    Prev
    Next
    INDEX
    Explanations

    limited components or data

    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
    âĹİ
    -0.09
    istrovstvÃŃ
    -0.09
    ARAM
    -0.09
     equipments
    -0.08
    longleftrightarrow
    -0.08
    âĺħâĺħ
    -0.08
     اتØŃاد
    -0.08
    iver
    -0.08
    asper
    -0.08
    füh
    -0.08
    POSITIVE LOGITS
     Parad
    0.11
     Anita
    0.09
     Mint
    0.09
    (æ°´
    0.08
    lements
    0.08
     Lamp
    0.08
     Xia
    0.08
     GRE
    0.08
     Alan
    0.08
     Tran
    0.08
    Activations Density 0.142%

    No Known Activations