© 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. 57618
    Prev
    Next
    INDEX
    Explanations

    addition and equations

    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
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.20
     GenerationType
    -0.13
    ÐIJÑĢÑħÑĸвовано
    -0.11
     FetchType
    -0.11
    chartInstance
    -0.09
    isContained
    -0.09
    íĨłíĨł
    -0.09
    ALCHEMY
    -0.09
    až
    -0.08
    ÑĥлÑİ
    -0.08
    POSITIVE LOGITS
    /-
    0.13
    alog
    0.10
    irs
    0.09
    odore
    0.09
    ÂĢÂĻ
    0.08
    ''''
    0.08
    idir
    0.08
    -\n
    0.08
    लब
    0.08
     indeb
    0.08
    Activations Density 0.111%

    No Known Activations