© 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. 38640
    Prev
    Next
    INDEX
    Explanations

    been involved

    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
    882
    -0.10
     sidelined
    -0.10
     divor
    -0.10
     Trot
    -0.09
    chia
    -0.09
    ahun
    -0.09
    被
    -0.09
     inher
    -0.09
    currently
    -0.09
     applauded
    -0.08
    POSITIVE LOGITS
     involved
    0.16
     instrumental
    0.13
     sight
    0.13
     featured
    0.12
     vocal
    0.12
    aver
    0.12
     compared
    0.11
     active
    0.11
    instrument
    0.11
     forthcoming
    0.11
    Activations Density 0.030%

    No Known Activations