© 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. 37981
    Prev
    Next
    INDEX
    Explanations

    ðŁĶ sequenceðŁĶ sequence detectionðŁĶ decoding sequence

    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
    âĶĢ
    -0.10
    teri
    -0.09
     à¸ģรà¸ģ
    -0.08
    aire
    -0.08
    ï¿
    -0.08
    ado
    -0.08
    ]âĢı
    -0.08
    ights
    -0.07
    omo
    -0.07
     Downing
    -0.07
    POSITIVE LOGITS
     labore
    0.08
     Plantae
    0.08
    ãĢħ
    0.08
    ukkit
    0.08
    /Foundation
    0.08
    à¸Ńà¸Ń
    0.08
    .getElements
    0.07
     hel
    0.07
    à¸Ļà¸Ń
    0.07
    _equalTo
    0.07
    Activations Density 0.005%

    No Known Activations