© 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. 35584
    Prev
    Next
    INDEX
    Explanations

    one and the other

    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
    Else
    -0.09
     Else
    -0.09
    ila
    -0.09
    ELSE
    -0.09
    outes
    -0.08
    :.:
    -0.08
    .additional
    -0.08
    Additional
    -0.08
    è¾
    -0.08
     Additional
    -0.08
    POSITIVE LOGITS
     another
    0.36
    ãĤĤãģĨ
    0.33
    åı¦ä¸Ģ
    0.33
     other
    0.30
     دÛĮگرÛĮ
    0.29
     others
    0.28
     otro
    0.27
    another
    0.27
    åı¦
    0.26
     Another
    0.26
    Activations Density 0.082%

    No Known Activations