© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    non-latin character sequences

    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
    otor
    -0.09
    a
    -0.09
    rou
    -0.09
    o
    -0.09
     cyclic
    -0.08
     STL
    -0.08
     Asc
    -0.08
     Tin
    -0.08
     caps
    -0.08
    rix
    -0.08
    POSITIVE LOGITS
    ียà¸Ķ
    0.11
    <|begin_of_text|>
    0.11
    anian
    0.10
    çĦ¶
    0.10
     tháºŃn
    0.10
    à¹ĩà¸Ī
    0.10
    ож
    0.10
    ãģĹãģĦ
    0.09
    격
    0.09
    .Areas
    0.09
    Activations Density 0.107%

    No Known Activations