© 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. 44215
    Prev
    Next
    INDEX
    Explanations

    programming instructions or code

    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
     latter
    -0.09
    ¼åIJĪ
    -0.08
    (s
    -0.08
     Mich
    -0.08
    -e
    -0.08
     ello
    -0.08
     Bes
    -0.07
    ®
    -0.07
    -any
    -0.07
     BST
    -0.07
    POSITIVE LOGITS
    <|begin_of_text|>
    0.09
    åİŁå§ĭ
    0.08
    ï¾Ĩï¾Ĩ
    0.08
    ĮĴ
    0.08
     ê°Ģì§Ģê³ł
    0.08
    ******č\n
    0.08
    .gb
    0.07
    :::::::::
    0.07
    wiÄħ
    0.07
     addCriterion
    0.07
    Activations Density 0.199%

    No Known Activations