Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65157
    Prev
    Next
    INDEX
    Explanations

    repair services and options

    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
     suppliers
    -0.10
    IBUT
    -0.10
     Sesso
    -0.10
     æı
    -0.09
     screenings
    -0.09
     Ing
    -0.09
    roupon
    -0.08
    æıĴ
    -0.08
    READING
    -0.08
    igit
    -0.08
    POSITIVE LOGITS
     training
    0.16
     technical
    0.15
     support
    0.14
    Technical
    0.13
    -training
    0.13
    training
    0.13
    Training
    0.13
    technical
    0.12
     Technical
    0.12
     Training
    0.12
    Activations Density 0.021%

    No Known Activations