© 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. 41070
    Prev
    Next
    INDEX
    Explanations

    excited announcements and invitations

    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
    kest
    -0.13
    丶
    -0.10
     impress
    -0.10
    /*č\n
    -0.09
     beaut
    -0.09
     Promise
    -0.08
     DOT
    -0.08
     promise
    -0.08
    cookie
    -0.08
     à¸ģรà¸ģ
    -0.08
    POSITIVE LOGITS
     pleased
    0.33
     pleasure
    0.29
    ple
    0.25
     proud
    0.23
     delighted
    0.19
     Ple
    0.17
     happy
    0.17
     plaisir
    0.17
    roud
    0.17
     ple
    0.17
    Activations Density 0.142%

    No Known Activations