© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1591
    Prev
    Next
    INDEX
    Explanations

    emphasis on specific topics

    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
    mana
    -0.10
    oves
    -0.09
     modern
    -0.09
     Keller
    -0.08
     society
    -0.08
     fal
    -0.08
     Lori
    -0.08
     culturally
    -0.08
    æĸ½
    -0.08
    518
    -0.08
    POSITIVE LOGITS
    ogle
    0.11
     compartment
    0.11
     consensus
    0.10
    /Dk
    0.09
     hierarchy
    0.09
    uteur
    0.09
     creature
    0.09
    intros
    0.09
     volunte
    0.09
     patron
    0.09
    Activations Density 0.080%

    No Known Activations