© 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. 2215
    Prev
    Next
    INDEX
    Explanations

    and then to

    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
    ifes
    -0.09
    èn
    -0.09
    ￣￣￣￣
    -0.09
    ucci
    -0.09
     heard
    -0.08
     iÅŁte
    -0.08
    ÐłÐĿ
    -0.08
    icontrol
    -0.08
    Await
    -0.08
     summon
    -0.08
    POSITIVE LOGITS
     soon
    0.16
     generally
    0.16
    soon
    0.13
     even
    0.13
     Soon
    0.12
     Generally
    0.12
    Soon
    0.12
    even
    0.12
     overall
    0.11
     sogar
    0.11
    Activations Density 0.043%

    No Known Activations