© 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. 34607
    Prev
    Next
    INDEX
    Explanations

    efforts to develop

    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
     environmentally
    -0.10
    507
    -0.10
     Cul
    -0.09
    raid
    -0.09
    jango
    -0.09
     environmental
    -0.09
     inher
    -0.09
    lea
    -0.09
     Sustainability
    -0.09
    dw
    -0.08
    POSITIVE LOGITS
     offset
    0.14
     offsets
    0.13
    offset
    0.11
     lobby
    0.11
     source
    0.11
    vol
    0.10
     regular
    0.10
     Lobby
    0.10
     eth
    0.10
     cage
    0.09
    Activations Density 0.006%

    No Known Activations