© 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. 25135
    Prev
    Next
    INDEX
    Explanations

    key-value mappings

    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
     function
    -0.10
    .fs
    -0.10
    chant
    -0.09
    ddl
    -0.09
     string
    -0.09
     Wer
    -0.09
    string
    -0.09
     const
    -0.09
     oss
    -0.09
    (string
    -0.09
    POSITIVE LOGITS
     addCriterion
    0.15
     java
    0.14
     J
    0.12
     thrown
    0.12
    .java
    0.11
     throws
    0.11
     jav
    0.10
     threw
    0.10
     boolean
    0.10
    java
    0.10
    Activations Density 0.080%

    No Known Activations