© 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. 38054
    Prev
    Next
    INDEX
    Explanations

    tender and award

    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
     operations
    -0.10
     Joh
    -0.10
    ieres
    -0.09
     shipments
    -0.09
     SOLD
    -0.08
     Warranty
    -0.08
     nom
    -0.08
     Conj
    -0.08
    é
    -0.08
    sold
    -0.08
    POSITIVE LOGITS
     tender
    0.36
     Tender
    0.31
     tend
    0.26
     awarded
    0.24
     award
    0.21
     bid
    0.21
    proc
    0.20
     awards
    0.19
    Proc
    0.19
     Award
    0.18
    Activations Density 0.094%

    No Known Activations