© 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. 3905
    Prev
    Next
    INDEX
    Explanations

    ram and computer memory

    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
     stagger
    -0.10
    anos
    -0.10
    ght
    -0.10
     Din
    -0.09
    ariate
    -0.09
    acman
    -0.09
    pets
    -0.09
    AMI
    -0.09
    anol
    -0.09
    -Russian
    -0.09
    POSITIVE LOGITS
    IFICATIONS
    0.17
    ifications
    0.14
    blings
    0.13
    ming
    0.13
    iscal
    0.12
    esses
    0.11
    bling
    0.11
    rod
    0.11
     Ram
    0.11
    isayar
    0.11
    Activations Density 0.018%

    No Known Activations