© 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. 41694
    Prev
    Next
    INDEX
    Explanations

    in grado di

    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
     regard
    -0.09
     consequence
    -0.09
     Lion
    -0.09
     Laud
    -0.09
     motivo
    -0.09
    ifies
    -0.09
     Miner
    -0.08
    eration
    -0.08
     lightning
    -0.08
     response
    -0.08
    POSITIVE LOGITS
     contact
    0.12
     disposition
    0.11
     mood
    0.11
     possession
    0.11
     position
    0.11
    contact
    0.11
     coma
    0.10
     disposed
    0.10
    ble
    0.10
    ibri
    0.10
    Activations Density 0.065%

    No Known Activations