© 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
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38519
    Prev
    Next
    INDEX
    Explanations

    perfect or ideal

    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
    umer
    -0.10
     impress
    -0.08
    oit
    -0.08
     desirable
    -0.08
    PrimaryKey
    -0.08
    Cpp
    -0.08
     valuable
    -0.08
    afil
    -0.08
     preval
    -0.08
     عبار
    -0.08
    POSITIVE LOGITS
     perfect
    0.92
    perfect
    0.68
     Perfect
    0.66
    Perfect
    0.63
     PERF
    0.62
     ideal
    0.54
    ideal
    0.43
    å®Į
    0.39
     Ideal
    0.38
     perfectly
    0.36
    Activations Density 0.161%

    No Known Activations