© 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. 44500
    Prev
    Next
    INDEX
    Explanations

    more more more

    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
    ãĤĪãĤĬ
    -0.10
     subt
    -0.10
     èī¯
    -0.10
    806
    -0.09
    èī¯
    -0.09
    som
    -0.09
    ripe
    -0.09
    ãģĵãĤĵãģ«
    -0.09
     Sommer
    -0.09
     strong
    -0.09
    POSITIVE LOGITS
     than
    0.22
     likely
    0.14
    -than
    0.14
    íĤ¹
    0.12
     difficult
    0.12
     niż
    0.12
     numerous
    0.11
     THAN
    0.11
    seo
    0.11
    than
    0.11
    Activations Density 0.029%

    No Known Activations