© 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. 60989
    Prev
    Next
    INDEX
    Explanations

    condensation, condense

    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
    otine
    -0.11
    iale
    -0.10
    aday
    -0.09
    ddb
    -0.09
    YTE
    -0.08
    amac
    -0.08
    .Actions
    -0.08
    ovny
    -0.08
    indsight
    -0.08
    ãģĹãģı
    -0.08
    POSITIVE LOGITS
     cond
    0.24
     Cond
    0.18
    -cond
    0.18
    cond
    0.16
    ensation
    0.16
     reaction
    0.15
    -type
    0.14
    Cond
    0.14
    (cond
    0.14
     kond
    0.14
    Activations Density 0.005%

    No Known Activations