© 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. 2708
    Prev
    Next
    INDEX
    Explanations

    necessary dependencies

    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
    _fore
    -0.10
     MIPS
    -0.10
     Neo
    -0.10
    fono
    -0.10
    loggedin
    -0.09
     CPUs
    -0.09
     OMAP
    -0.09
    cps
    -0.09
     cpu
    -0.09
    krom
    -0.09
    POSITIVE LOGITS
     NV
    0.17
     cu
    0.17
     Pascal
    0.16
     cud
    0.15
    cu
    0.15
     Tesla
    0.15
     nv
    0.15
     drivers
    0.14
    nv
    0.14
    _nv
    0.14
    Activations Density 0.112%

    No Known Activations