© 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. 42900
    Prev
    Next
    INDEX
    Explanations

    provide alternative options

    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
     Dank
    -0.10
     Valent
    -0.10
     reused
    -0.10
    uld
    -0.09
     reuse
    -0.09
     additions
    -0.09
    iet
    -0.09
     reusable
    -0.08
    orden
    -0.08
    yled
    -0.08
    POSITIVE LOGITS
     alternative
    0.39
     alternatives
    0.33
    alternative
    0.30
     Alternative
    0.29
    Alternative
    0.26
     alternate
    0.25
     substitute
    0.23
     Altern
    0.23
     altern
    0.22
    代
    0.21
    Activations Density 0.230%

    No Known Activations