© 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
    5. 50-RESID-POST-GF
    7. 33893
    Prev
    Next
    INDEX
    Explanations

    preposition followed by specific nouns

    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
    odata
    -0.08
     zbyt
    -0.08
    /Dk
    -0.08
    asl
    -0.07
     NUIT
    -0.07
    celik
    -0.07
     dziewcz
    -0.07
    ichier
    -0.07
    izik
    -0.07
    ãĤĬãģ¨
    -0.07
    POSITIVE LOGITS
     modern
    0.09
     '
    0.09
     US
    0.08
     any
    0.08
     stuff
    0.08
     spect
    0.08
     USA
    0.08
    nze
    0.08
     e
    0.08
     недел
    0.08
    Activations Density 2.248%

    No Known Activations