© 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. 15043
    Prev
    Next
    INDEX
    Explanations

    exploring history, causes, and problems

    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
     possibilities
    -0.11
    åı¯èĥ½æĢ§
    -0.10
    ende
    -0.09
    acic
    -0.09
    ijkstra
    -0.08
    Fatal
    -0.08
     exceptional
    -0.08
     Fatal
    -0.08
     cdecl
    -0.08
    ạp
    -0.08
    POSITIVE LOGITS
     causes
    0.25
     Causes
    0.20
     magnitude
    0.20
     problem
    0.20
     root
    0.19
     extent
    0.19
     prevalence
    0.18
    magnitude
    0.17
     statistics
    0.17
     Problem
    0.17
    Activations Density 0.117%

    No Known Activations