© 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. 44426
    Prev
    Next
    INDEX
    Explanations

    if ever or any

    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
    ijľ
    -0.10
     Overse
    -0.09
    oki
    -0.09
     právÄĽ
    -0.09
    ahas
    -0.09
    786
    -0.09
     Lawson
    -0.08
    eph
    -0.08
    ately
    -0.08
    žel
    -0.08
    POSITIVE LOGITS
     ever
    0.33
     need
    0.22
    ever
    0.22
     EVER
    0.20
     besoin
    0.19
    -ever
    0.18
    éľĢè¦ģ
    0.18
     cần
    0.18
     needed
    0.18
     any
    0.17
    Activations Density 0.041%

    No Known Activations