© 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. 43994
    Prev
    Next
    INDEX
    Explanations

    alternate realities and dimensions

    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
    geme
    -0.09
    uzzi
    -0.09
     dynam
    -0.09
     Dyn
    -0.08
     descent
    -0.08
     vit
    -0.08
     Circle
    -0.08
    enco
    -0.08
    zet
    -0.08
    (çģ«
    -0.08
    POSITIVE LOGITS
     dimension
    0.25
     alternate
    0.24
     universe
    0.22
     parallel
    0.22
     univers
    0.22
     dimensions
    0.21
     Alternate
    0.20
     Parallel
    0.19
    Parallel
    0.18
    alternate
    0.18
    Activations Density 0.108%

    No Known Activations