© 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. 17514
    Prev
    Next
    INDEX
    Explanations

    sequence of events

    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
     Flo
    -0.09
    stab
    -0.09
     rud
    -0.09
    ingu
    -0.08
    rement
    -0.08
     stab
    -0.08
    riage
    -0.08
    tails
    -0.08
     rule
    -0.08
     simultaneous
    -0.08
    POSITIVE LOGITS
     sequence
    0.55
    sequence
    0.45
     Sequence
    0.41
     chain
    0.41
    Sequence
    0.38
     sequences
    0.36
    _sequence
    0.34
     events
    0.32
     series
    0.32
    .sequence
    0.30
    Activations Density 0.245%

    No Known Activations