© 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. 44506
    Prev
    Next
    INDEX
    Explanations

    structured data labels

    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
    ¦æĥħ
    -0.11
    upp
    -0.09
    oeff
    -0.09
    Porn
    -0.09
    ipi
    -0.08
    Ø
    -0.08
    ÂĢÂĢ
    -0.08
    vÄĽd
    -0.08
     Pur
    -0.08
    .Formatter
    -0.08
    POSITIVE LOGITS
     unnamed
    0.10
    érc
    0.08
     nackte
    0.08
    ContextHolder
    0.08
     Vend
    0.08
     Judy
    0.07
    alli
    0.07
    OVE
    0.07
    ___
    0.07
    IKE
    0.07
    Activations Density 0.075%

    No Known Activations