© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29314
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    idon
    -0.09
     Herz
    -0.09
     поÑħ
    -0.09
     exponential
    -0.09
    uent
    -0.09
    se
    -0.08
    ´:
    -0.08
     McCart
    -0.08
     Deliver
    -0.08
    ades
    -0.08
    POSITIVE LOGITS
    ãĥ»ãĥ»ãĥ»\n\n
    0.09
    krv
    0.09
    .MixedReality
    0.09
    å°¾
    0.09
    Sensitive
    0.09
    çĵ¦
    0.08
    senal
    0.08
    printStats
    0.08
    886
    0.08
    lisi
    0.08
    Activations Density 0.249%

    No Known Activations