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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45153
    Prev
    Next
    INDEX
    Explanations

    will get lost or approaching

    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
     Hurt
    -0.11
     flights
    -0.11
    orno
    -0.11
     jet
    -0.10
     round
    -0.10
    Jet
    -0.10
     Jet
    -0.10
     stale
    -0.09
     Cul
    -0.09
     choke
    -0.09
    POSITIVE LOGITS
     listing
    0.14
     caps
    0.14
    æ²ī
    0.13
     Listing
    0.13
     engine
    0.13
     punct
    0.13
     strand
    0.13
     disabled
    0.12
     structural
    0.12
     crash
    0.12
    Activations Density 0.062%

    No Known Activations