© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 33965
    Prev
    Next
    INDEX
    Explanations

    garbage collection or forceful termination

    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
    èķ
    -0.10
     Legs
    -0.10
    çĵľ
    -0.09
    junction
    -0.08
     VOID
    -0.08
    legs
    -0.08
    ertia
    -0.08
     caching
    -0.08
    imedia
    -0.08
     JsonRequestBehavior
    -0.08
    POSITIVE LOGITS
     GC
    0.33
     garbage
    0.30
     Gar
    0.30
    GC
    0.29
     gc
    0.29
    gc
    0.27
    Gar
    0.24
    gar
    0.23
    .gc
    0.23
    åŀ
    0.22
    Activations Density 0.025%

    No Known Activations