© 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. 31169
    Prev
    Next
    INDEX
    Explanations

    European Organization for Nuclear Research

    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
     Blow
    -0.10
    bic
    -0.10
    -mar
    -0.09
     astronom
    -0.09
     blow
    -0.09
     rou
    -0.09
     Chun
    -0.09
     Dynam
    -0.08
     Finger
    -0.08
     dynam
    -0.08
    POSITIVE LOGITS
     particle
    0.22
     Large
    0.18
     Particle
    0.17
     particles
    0.17
    particle
    0.16
    CMS
    0.15
     collider
    0.15
     CMS
    0.15
    Particle
    0.15
    ollider
    0.15
    Activations Density 0.017%

    No Known Activations