© 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 (Instruct)
    3. 50-RESID-POST-GF
    4. 38137
    Prev
    Next
    INDEX
    Explanations

    Nanital Pangot

    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
    alem
    -0.11
    cala
    -0.10
     IKE
    -0.09
     tô
    -0.09
     Oregon
    -0.09
    å²
    -0.09
     Karnataka
    -0.09
    _intf
    -0.09
     diagon
    -0.09
     Kore
    -0.09
    POSITIVE LOGITS
     Utt
    0.14
     Josh
    0.13
     Denver
    0.13
     Teh
    0.12
     Weber
    0.11
     Himal
    0.10
     Luck
    0.10
     Meer
    0.10
    hrad
    0.10
    Denver
    0.10
    Activations Density 0.027%

    No Known Activations