© 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. 44652
    Prev
    Next
    INDEX
    Explanations

    stage

    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
    ilen
    -0.11
     Schro
    -0.09
     onboard
    -0.09
    adir
    -0.09
     åº
    -0.08
    nici
    -0.08
    iano
    -0.08
     bench
    -0.08
     Ferguson
    -0.08
    acket
    -0.08
    POSITIVE LOGITS
     stage
    0.71
    stage
    0.50
    -stage
    0.49
     Stage
    0.48
    Stage
    0.46
     stages
    0.43
    .stage
    0.42
    _stage
    0.41
    \tstage
    0.38
    (stage
    0.38
    Activations Density 0.068%

    No Known Activations