© 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. 38060
    Prev
    Next
    INDEX
    Explanations

    predict maintenance needs or prevent breakdowns

    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
     Kee
    -0.10
     lever
    -0.09
    technology
    -0.09
     Goodman
    -0.09
     toll
    -0.09
     technological
    -0.09
    adamente
    -0.09
    alis
    -0.09
     technology
    -0.08
    apan
    -0.08
    POSITIVE LOGITS
     automatically
    0.16
     Automatically
    0.12
     based
    0.12
     AI
    0.12
    Îŀ
    0.10
     dá»±a
    0.10
     automáticamente
    0.09
    _UNUSED
    0.09
    .synthetic
    0.09
    Ops
    0.09
    Activations Density 0.099%

    No Known Activations