© 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. 34565
    Prev
    Next
    INDEX
    Explanations

    software engineer, economic narratives, service platforms, driving school, privacy advocate, lockdown browser, text ads

    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
    _tE
    -0.09
    izik
    -0.09
     Ðŀдна
    -0.09
    <|begin_of_text|>
    -0.09
     Verfüg
    -0.08
    @nate
    -0.08
    .want
    -0.08
     jenter
    -0.08
    esiz
    -0.08
     zastav
    -0.08
    POSITIVE LOGITS
    tal
    0.09
    ran
    0.09
    er
    0.09
     Company
    0.08
     fore
    0.08
     Perc
    0.08
    agi
    0.08
    339
    0.08
    m
    0.08
     thu
    0.08
    Activations Density 0.232%

    No Known Activations