© 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. 37944
    Prev
    Next
    INDEX
    Explanations

    They are known for their

    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
    ypes
    -0.10
     Mar
    -0.09
     av
    -0.09
    ëĪĦ
    -0.09
     mar
    -0.09
    ains
    -0.09
     siblings
    -0.09
    .hashCode
    -0.09
     auth
    -0.08
     Tort
    -0.08
    POSITIVE LOGITS
     lived
    0.15
     living
    0.13
     sá»ijng
    0.13
     жив
    0.11
    -lived
    0.11
     live
    0.11
     spend
    0.11
    weigh
    0.11
    living
    0.11
     prefer
    0.10
    Activations Density 0.085%

    No Known Activations