© 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. 29453
    Prev
    Next
    INDEX
    Explanations

    all machines, hosts, servers

    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
     Software
    -0.12
     SOFTWARE
    -0.10
     software
    -0.10
    Software
    -0.10
     Madonna
    -0.09
     workstation
    -0.09
     Lorenzo
    -0.09
    INDER
    -0.09
    ongs
    -0.09
     Paradise
    -0.09
    POSITIVE LOGITS
     machine
    0.30
     machines
    0.26
    machine
    0.22
     Machine
    0.18
     box
    0.18
    achine
    0.17
     host
    0.17
    _machine
    0.17
    Machine
    0.17
     маÑĪи
    0.16
    Activations Density 0.134%

    No Known Activations