© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36608
    Prev
    Next
    INDEX
    Explanations

    por lo que / por lo tanto

    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
     Lama
    -0.09
    uzz
    -0.09
    ucz
    -0.09
    deg
    -0.08
    col
    -0.08
     compromise
    -0.08
    OMET
    -0.08
     primitives
    -0.08
    dcc
    -0.08
    avic
    -0.08
    POSITIVE LOGITS
    iguiente
    0.16
     therefore
    0.14
     Therefore
    0.12
    ¶Į
    0.11
     tanto
    0.11
    ï¼ĮæīĢ以
    0.10
    æīĢ以
    0.10
     reason
    0.10
     so
    0.10
     ende
    0.10
    Activations Density 0.009%

    No Known Activations