© 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. 38762
    Prev
    Next
    INDEX
    Explanations

    executed in order

    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
     Herc
    -0.10
    Parallel
    -0.10
     subordinate
    -0.09
     Hayward
    -0.09
     Parallel
    -0.09
     parallel
    -0.09
     simultaneous
    -0.09
    parallel
    -0.09
     cycles
    -0.08
    _parallel
    -0.08
    POSITIVE LOGITS
     linear
    0.25
     sequence
    0.25
     serial
    0.22
    éłĨ
    0.21
    顺
    0.21
     chain
    0.21
     Linear
    0.21
     sequ
    0.20
    Linear
    0.20
    åºı
    0.20
    Activations Density 0.194%

    No Known Activations