© 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. 39120
    Prev
    Next
    INDEX
    Explanations

    's followed by state or ongoing action

    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
    appen
    -0.10
    ’;ve
    -0.10
     underwent
    -0.09
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.09
    've
    -0.09
    SEA
    -0.08
    ÅĽmy
    -0.08
    asco
    -0.08
    RM
    -0.08
     Happ
    -0.08
    POSITIVE LOGITS
     been
    0.29
    been
    0.24
     Been
    0.23
     BEEN
    0.23
     got
    0.21
    Been
    0.21
    got
    0.19
     sido
    0.18
    Got
    0.17
     été
    0.15
    Activations Density 0.055%

    No Known Activations