© 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. 3283
    Prev
    Next
    INDEX
    Explanations

    spending hours or days

    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
     Moment
    -0.11
     daytime
    -0.10
    egot
    -0.09
    Viá»ĩc
    -0.09
    alink
    -0.09
     intermittent
    -0.08
    olah
    -0.08
    269
    -0.08
    ohn
    -0.08
    809
    -0.08
    POSITIVE LOGITS
     hours
    0.18
     sometimes
    0.16
     late
    0.16
     whenever
    0.15
     hour
    0.12
     often
    0.12
     bazen
    0.12
    ometimes
    0.12
    sometimes
    0.12
    Hours
    0.12
    Activations Density 0.103%

    No Known Activations