© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34911
    Prev
    Next
    INDEX
    Explanations

    NAME_X references

    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
    splash
    -0.10
    ReturnValue
    -0.09
    tae
    -0.08
    Splash
    -0.08
     sayılı
    -0.08
    icus
    -0.08
    affles
    -0.08
    umbn
    -0.08
    DTV
    -0.08
     Splash
    -0.07
    POSITIVE LOGITS
    plate
    0.10
    itor
    0.08
    ufact
    0.08
     "
    0.08
    plates
    0.08
     \"
    0.08
    eer
    0.08
    intern
    0.08
    ake
    0.08
     bet
    0.08
    Activations Density 0.081%

    No Known Activations