© 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. 58415
    Prev
    Next
    INDEX
    Explanations

    in followed by noun or location

    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
    ekk
    -0.09
     seasonal
    -0.08
    antic
    -0.08
    vyk
    -0.08
     cancel
    -0.08
    ClientId
    -0.08
     Ley
    -0.07
    angkan
    -0.07
     å»
    -0.07
    chie
    -0.07
    POSITIVE LOGITS
     both
    0.10
     three
    0.09
    ÂŁ
    0.09
     two
    0.09
    _both
    0.08
     areas
    0.08
     central
    0.08
     parts
    0.08
     SI
    0.08
    ModelProperty
    0.08
    Activations Density 0.160%

    No Known Activations