© 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. 39864
    Prev
    Next
    INDEX
    Explanations

    can help or assist

    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
     ãĢī
    -0.10
     transient
    -0.10
    agh
    -0.09
     Guth
    -0.09
     cri
    -0.09
     bene
    -0.09
     Keystone
    -0.08
    cri
    -0.08
    swick
    -0.08
    POSITIVE LOGITS
     help
    0.24
     assistance
    0.23
    帮
    0.20
     assist
    0.20
     giúp
    0.18
     helped
    0.18
    帮åĬ©
    0.18
     assists
    0.17
     Assistance
    0.16
     Help
    0.16
    Activations Density 0.027%

    No Known Activations