© 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. 34034
    Prev
    Next
    INDEX
    Explanations

    articles and linking verbs

    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
     поба
    -0.13
     vede
    -0.10
     chce
    -0.09
     είÏĩαν
    -0.09
    éĥ½ä¼ļ
    -0.09
    à¸Ķร
    -0.09
     sẽ
    -0.08
    å°±ä¼ļ
    -0.08
    abil
    -0.08
    yd
    -0.08
    POSITIVE LOGITS
     usually
    0.12
    被
    0.12
     fung
    0.12
     usual
    0.11
     consist
    0.11
     被
    0.11
    æĺ¯ä¸Ģ
    0.10
     prov
    0.10
    æĺ¯æĪij
    0.10
     poss
    0.10
    Activations Density 0.150%

    No Known Activations