© 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. 98
    Prev
    Next
    INDEX
    Explanations

    Scrum framework and team

    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
     Pey
    -0.11
     Modular
    -0.11
     modular
    -0.10
    oon
    -0.09
     vet
    -0.09
    het
    -0.09
     bread
    -0.09
     Ethnic
    -0.09
     Vet
    -0.09
    alis
    -0.09
    POSITIVE LOGITS
     Sc
    0.23
     scr
    0.22
     SCR
    0.17
     Kan
    0.16
    Sc
    0.15
     Sprint
    0.15
     kan
    0.14
     sprint
    0.14
    printStats
    0.14
    SCR
    0.14
    Activations Density 0.052%

    No Known Activations