© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44307
    Prev
    Next
    INDEX
    Explanations

    leading to choices or doors

    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
    CHIP
    -0.11
     crossings
    -0.10
    erb
    -0.10
     âĵĺ
    -0.09
    ystack
    -0.09
     highways
    -0.09
    orners
    -0.09
     DRIVE
    -0.09
    fragistics
    -0.09
    Corner
    -0.09
    POSITIVE LOGITS
     leads
    0.22
     leading
    0.18
    leads
    0.17
     fork
    0.16
     exit
    0.15
     Leads
    0.15
     door
    0.15
    leading
    0.15
     lead
    0.14
    -leading
    0.14
    Activations Density 0.046%

    No Known Activations