© 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. 30516
    Prev
    Next
    INDEX
    Explanations

    pronouns prompting action or guidance

    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
     compreh
    -0.10
    gether
    -0.10
     help
    -0.10
     allow
    -0.09
    ying
    -0.09
    alsa
    -0.09
     ï¾Ĭ
    -0.09
    aza
    -0.09
    alama
    -0.08
    emplates
    -0.08
    POSITIVE LOGITS
    /us
    0.20
     να
    0.13
    /her
    0.13
    zelf
    0.12
    åĢij
    0.11
    /my
    0.10
    esy
    0.10
    à¹ĥà¸Ļà¸ģาร
    0.10
     to
    0.09
    -même
    0.09
    Activations Density 0.036%

    No Known Activations