Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34279
    Prev
    Next
    INDEX
    Explanations

    narrowing 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
     flattened
    -0.11
     weakening
    -0.10
     lowering
    -0.10
     LOWER
    -0.10
     Minh
    -0.10
     Lower
    -0.09
     lowers
    -0.09
     Depths
    -0.09
    Nh
    -0.09
     flatt
    -0.09
    POSITIVE LOGITS
     narrow
    0.40
     Narrow
    0.37
     nar
    0.30
     narrowed
    0.29
     ì¢
    0.27
     Nar
    0.24
    nar
    0.24
     wh
    0.23
     narrower
    0.23
    缩
    0.23
    Activations Density 0.184%

    No Known Activations