© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 33971
    Prev
    Next
    INDEX
    Explanations

    web search

    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
    WithData
    -0.10
    SearchParams
    -0.09
    éĥ
    -0.09
     forcefully
    -0.08
     explosive
    -0.08
    иденÑĤ
    -0.08
     Foster
    -0.08
    âłĢ
    -0.08
    upert
    -0.08
    ī´
    -0.08
    POSITIVE LOGITS
     online
    0.17
     engines
    0.13
     information
    0.13
     internet
    0.13
     topics
    0.12
     engine
    0.12
    online
    0.12
     Engine
    0.11
     info
    0.11
    /google
    0.11
    Activations Density 0.091%

    No Known Activations