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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 501
    Prev
    Next
    INDEX
    Explanations

    reference and citing

    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
    amarin
    -0.08
     detail
    -0.08
    ricks
    -0.08
    .removeListener
    -0.08
    æıı
    -0.08
    §Ãĥ
    -0.08
    929
    -0.08
    icture
    -0.08
     Robots
    -0.08
    ibi
    -0.08
    POSITIVE LOGITS
     reference
    0.35
    å¼ķçĶ¨
    0.32
     refer
    0.27
    reference
    0.27
    åıĤèĢĥ
    0.27
    -reference
    0.25
     references
    0.25
     refers
    0.24
    Reference
    0.24
     Reference
    0.24
    Activations Density 0.207%

    No Known Activations