© 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. 61724
    Prev
    Next
    INDEX
    Explanations

    rates per unit

    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
     Perf
    -0.16
     annual
    -0.11
    Perm
    -0.11
     yearly
    -0.11
    _perf
    -0.11
     Annual
    -0.10
    _perm
    -0.10
    #ad
    -0.10
     perf
    -0.10
    /per
    -0.10
    POSITIVE LOGITS
     per
    0.88
    _per
    0.38
    per
    0.38
     пеÑĢ
    0.31
     ÙĦÙĥÙĦ
    0.29
    ëĭ¹
    0.26
     baÅŁÄ±na
    0.26
    PerPage
    0.24
     each
    0.23
    .per
    0.21
    Activations Density 0.191%

    No Known Activations