© 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. 38699
    Prev
    Next
    INDEX
    Explanations

    harmful or offensive content

    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
    ĮĴ
    -0.10
    âĦĸâĦĸ
    -0.10
    ãİ
    -0.09
    надлеж
    -0.09
    âĶ´
    -0.09
    iesel
    -0.09
    Ctrls
    -0.09
    obao
    -0.09
    «ĺ
    -0.08
    ÏĦαι
    -0.08
    POSITIVE LOGITS
    ifice
    0.14
     hurt
    0.13
     potentially
    0.12
    atory
    0.12
    ific
    0.11
    ator
    0.11
    !
    0.11
     otherwise
    0.10
    acles
    0.10
    ien
    0.10
    Activations Density 0.048%

    No Known Activations