© 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. 55475
    Prev
    Next
    INDEX
    Explanations

    introducing goals with objective:

    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
    tract
    -0.11
    wich
    -0.09
    ldb
    -0.09
    ARP
    -0.09
     Äijiá»ĥn
    -0.09
    ingham
    -0.09
    ilha
    -0.09
    oller
    -0.09
    isbury
    -0.09
     Sır
    -0.09
    POSITIVE LOGITS
    ives
    0.15
    ivos
    0.13
    ive
    0.11
    ektiv
    0.11
    zza
    0.11
    -object
    0.10
    /Object
    0.10
    ection
    0.10
     promin
    0.10
    IVES
    0.10
    Activations Density 0.027%

    No Known Activations