© 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. 33112
    Prev
    Next
    INDEX
    Explanations

    specific or extended periods of time

    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
     Timing
    -0.13
     timing
    -0.12
    Timing
    -0.12
     timed
    -0.12
    timing
    -0.11
     Lifetime
    -0.10
    Lifetime
    -0.10
    ucht
    -0.10
     chronological
    -0.10
    ongo
    -0.09
    POSITIVE LOGITS
     period
    0.72
    period
    0.42
     Period
    0.42
     periodo
    0.40
    Period
    0.38
    æľŁ
    0.38
     пеÑĢиод
    0.38
     periods
    0.37
    _period
    0.36
     interval
    0.36
    Activations Density 0.113%

    No Known Activations