© 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. 44454
    Prev
    Next
    INDEX
    Explanations

    Canadian and Canadian-American relations

    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
    ï½Ĵ
    -0.10
     ãĢĢ
    -0.10
    kip
    -0.10
    ATUS
    -0.09
    ONTAL
    -0.09
    IBUT
    -0.09
     Tender
    -0.09
    rå
    -0.08
    ured
    -0.08
     Renew
    -0.08
    POSITIVE LOGITS
     Goose
    0.18
    igua
    0.17
     Tire
    0.17
     Rockies
    0.15
     goose
    0.15
     maple
    0.14
     Canadian
    0.13
     Toronto
    0.13
     Eh
    0.13
    Canadian
    0.13
    Activations Density 0.022%

    No Known Activations