© 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
    5. 50-RESID-POST-GF
    7. 33951
    Prev
    Next
    INDEX
    Explanations

    must followed by directive

    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
    à¸ŀà¸ļ
    -0.10
    _iff
    -0.10
    ÂĢÂĢ
    -0.10
     mesel
    -0.09
    EMPLARY
    -0.09
    ¦æĥħ
    -0.09
    à¸ģว
    -0.09
    unk
    -0.09
     PROFITS
    -0.08
    -alist
    -0.08
    POSITIVE LOGITS
    n
    0.19
    ache
    0.13
     MUST
    0.13
    must
    0.13
    ering
    0.12
     Must
    0.12
     must
    0.12
     always
    0.12
    s
    0.12
    aches
    0.11
    Activations Density 0.058%

    No Known Activations