© 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. 56012
    Prev
    Next
    INDEX
    Explanations

    Harry Potter wizardry adventures

    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
    olla
    -0.10
    uco
    -0.10
    irez
    -0.09
    .struts
    -0.09
     Guild
    -0.09
     Cors
    -0.09
     Bunny
    -0.08
     cors
    -0.08
     Alphabet
    -0.08
    WARE
    -0.08
    POSITIVE LOGITS
     Harry
    0.33
    Harry
    0.29
     Potter
    0.24
     wand
    0.20
    wand
    0.19
     wizard
    0.18
    umbledore
    0.17
    oldemort
    0.17
     Hogwarts
    0.17
     HP
    0.16
    Activations Density 0.040%

    No Known Activations