© 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. 38595
    Prev
    Next
    INDEX
    Explanations

    experiment with different options

    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
    riot
    -0.09
     EITHER
    -0.09
     Either
    -0.09
     hundreds
    -0.09
    ONO
    -0.08
    otechn
    -0.08
    ledger
    -0.08
    ách
    -0.08
    .inflate
    -0.08
    pes
    -0.08
    POSITIVE LOGITS
     several
    0.23
     Several
    0.18
    Several
    0.17
    åĩłä¸ª
    0.16
    åĩł
    0.16
     different
    0.15
     varios
    0.14
     few
    0.14
     nÄĽkolika
    0.14
     multiple
    0.13
    Activations Density 0.022%

    No Known Activations