© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs

    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
    520
    -0.10
    ONSE
    -0.09
    ollo
    -0.09
    yna
    -0.09
     Pers
    -0.09
     Gear
    -0.09
    yle
    -0.08
     Snyder
    -0.08
    ookie
    -0.08
     WF
    -0.08
    POSITIVE LOGITS
     saw
    0.13
     noticed
    0.13
     couldn
    0.12
     notice
    0.12
     hope
    0.11
    noticed
    0.11
     Saw
    0.11
    .notice
    0.11
     Notice
    0.10
     just
    0.10
    Activations Density 0.036%

    No Known Activations