© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44414
    Prev
    Next
    INDEX
    Explanations

    responsive dashboard, AWS API, programming language

    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
    -
    -0.08
     isp
    -0.08
    bourg
    -0.08
    -be
    -0.07
     _$
    -0.07
     Chi
    -0.07
    .Localization
    -0.07
     PH
    -0.07
     PR
    -0.07
     DO
    -0.07
    POSITIVE LOGITS
     -*-č\n
    0.10
    ¶Į
    0.09
    ughs
    0.08
    eç
    0.08
    icens
    0.08
    .scalablytyped
    0.08
    infeld
    0.08
    .mybatisplus
    0.07
    .vertx
    0.07
    ãģĸ
    0.07
    Activations Density 0.053%

    No Known Activations