© 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. 59009
    Prev
    Next
    INDEX
    Explanations

    former abandoned lair

    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
     bosses
    -0.16
     boss
    -0.15
    Boss
    -0.13
     rulers
    -0.11
     president
    -0.11
     Authorities
    -0.11
     ÑħозÑı
    -0.11
     Boss
    -0.11
     emperor
    -0.11
    boss
    -0.11
    POSITIVE LOGITS
     court
    0.20
     advisors
    0.19
     Advisors
    0.18
     subjects
    0.17
     loyal
    0.17
     Court
    0.17
     advisor
    0.16
     trusted
    0.16
    èĩ£
    0.16
     retain
    0.15
    Activations Density 0.063%

    No Known Activations