© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43788
    Prev
    Next
    INDEX
    Explanations

    developmental conditions occur when

    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
     Duration
    -0.11
     Kür
    -0.11
    Periph
    -0.11
     infl
    -0.10
     Frontier
    -0.10
     Parkinson
    -0.10
    :y
    -0.10
     derec
    -0.10
    SetActive
    -0.10
     duration
    -0.09
    POSITIVE LOGITS
     Down
    0.23
    intel
    0.19
     intellectual
    0.19
    Intel
    0.18
     Intellectual
    0.18
     Intel
    0.17
     intellect
    0.17
    Down
    0.17
     developmental
    0.16
     Development
    0.16
    Activations Density 0.020%

    No Known Activations