© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43323
    Prev
    Next
    INDEX
    Explanations

    previously or before

    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
    /current
    -0.10
     CURRENT
    -0.10
    .hasNext
    -0.09
     пока
    -0.09
    abil
    -0.09
     successors
    -0.09
    Current
    -0.09
     EITHER
    -0.09
    CURRENT
    -0.08
    plex
    -0.08
    POSITIVE LOGITS
     earlier
    0.57
     Earlier
    0.41
    Earlier
    0.40
    ear
    0.32
     anterior
    0.30
     ÑĢан
    0.29
     ear
    0.25
     ÑĢанÑĮÑĪе
    0.25
     before
    0.24
    ább
    0.24
    Activations Density 0.083%

    No Known Activations