© 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. 63203
    Prev
    Next
    INDEX
    Explanations

    he had always

    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
     actually
    -0.10
     advance
    -0.09
    265
    -0.09
    ÃŃsto
    -0.08
     quant
    -0.08
    actually
    -0.08
     Commun
    -0.08
     slept
    -0.08
    ongo
    -0.08
     nas
    -0.08
    POSITIVE LOGITS
     altijd
    0.14
     вÑģегда
    0.13
     always
    0.12
     luôn
    0.12
     pride
    0.12
    always
    0.12
     seemed
    0.11
     toujours
    0.11
     sempre
    0.11
     vždy
    0.11
    Activations Density 0.113%

    No Known Activations