© 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. 38535
    Prev
    Next
    INDEX
    Explanations

    possessive noun phrases

    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
     country
    -0.16
    country
    -0.11
    aland
    -0.11
     planet
    -0.11
     ülkenin
    -0.11
     kingdom
    -0.11
     paÃŃs
    -0.11
     careers
    -0.10
     nation
    -0.10
     continent
    -0.09
    POSITIVE LOGITS
     behalf
    0.14
     premier
    0.12
     own
    0.12
     inhabitants
    0.11
     top
    0.11
     finest
    0.11
    ÂĢÂĻ
    0.10
    '
    0.10
     Fin
    0.10
     conscience
    0.10
    Activations Density 0.054%

    No Known Activations