© 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. 14014
    Prev
    Next
    INDEX
    Explanations

    failure, collapsed, broke down

    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
     absent
    -0.12
     recently
    -0.10
     rest
    -0.10
     canv
    -0.09
    iani
    -0.09
    caf
    -0.09
     lately
    -0.09
     replaced
    -0.09
    feld
    -0.08
     used
    -0.08
    POSITIVE LOGITS
     failed
    0.25
     ultimately
    0.25
    失败
    0.25
     fail
    0.23
    Ultimately
    0.22
     fails
    0.21
     failure
    0.21
     never
    0.20
    failed
    0.20
     Failed
    0.20
    Activations Density 0.093%

    No Known Activations