© 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. 38708
    Prev
    Next
    INDEX
    Explanations

    chemical industry compounds

    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
     ammonia
    -0.11
     Amar
    -0.11
     Shoe
    -0.09
    elop
    -0.09
     oxid
    -0.09
     Guill
    -0.09
     shareholder
    -0.09
    _SELECTION
    -0.09
    zew
    -0.09
    elman
    -0.09
    POSITIVE LOGITS
     est
    0.41
    ester
    0.26
     Est
    0.23
    esters
    0.22
    ’;est
    0.21
    'est
    0.21
     EST
    0.20
    Est
    0.20
    .est
    0.18
     Esther
    0.17
    Activations Density 0.142%

    No Known Activations