© 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. 2134
    Prev
    Next
    INDEX
    Explanations

    remember, mind, forget, attention

    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
    izik
    -0.09
    kea
    -0.09
    amen
    -0.09
     Receipt
    -0.09
    üzel
    -0.08
    createTime
    -0.08
    įng
    -0.08
    ãĢĶ
    -0.08
     Morrow
    -0.08
    inki
    -0.08
    POSITIVE LOGITS
     throughout
    0.09
     bre
    0.09
     bahwa
    0.09
    ::.
    0.09
    ä»
    0.08
     yourself
    0.08
    zell
    0.08
     Limited
    0.08
     treat
    0.08
    :
    0.08
    Activations Density 0.098%

    No Known Activations