© 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. 18153
    Prev
    Next
    INDEX
    Explanations

    if you want

    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
     Magnum
    -0.10
     foregoing
    -0.09
    icer
    -0.09
     каз
    -0.09
    esthes
    -0.09
     dood
    -0.08
    erson
    -0.08
    alf
    -0.08
    strcasecmp
    -0.08
    comed
    -0.08
    POSITIVE LOGITS
     encounter
    0.16
     ever
    0.14
     wish
    0.13
     prefer
    0.13
     Encounter
    0.13
     decide
    0.12
     already
    0.12
     wishes
    0.12
    éľĢè¦ģ
    0.12
     Wish
    0.11
    Activations Density 0.040%

    No Known Activations