© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34562
    Prev
    Next
    INDEX
    Explanations

    modal verb or 'to' followed by verb

    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
    ppe
    -0.10
    oure
    -0.10
    åŃĺäºİ
    -0.09
    ktop
    -0.09
    845
    -0.09
    对äºİ
    -0.09
    acin
    -0.08
    isNew
    -0.08
    icter
    -0.08
    ;;;;;;
    -0.08
    POSITIVE LOGITS
    äºĪ
    0.13
     Nearby
    0.12
    åĪłéϤæĪIJåĬŁ
    0.11
    iez
    0.11
    åħ¶ä¸Ń
    0.11
     nearby
    0.10
     Sle
    0.10
     obliged
    0.10
     provide
    0.09
     dess
    0.09
    Activations Density 0.204%

    No Known Activations