© 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. 44531
    Prev
    Next
    INDEX
    Explanations

    manipulative techniques

    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
     discretion
    -0.10
    ikip
    -0.09
     Coc
    -0.09
     Discrim
    -0.09
     counterfeit
    -0.08
    olen
    -0.08
    æĨ
    -0.08
     Foster
    -0.08
    tim
    -0.08
     ritual
    -0.08
    POSITIVE LOGITS
     techniques
    0.24
    Manip
    0.23
     manip
    0.23
     Manip
    0.23
     manipulation
    0.21
     Techniques
    0.20
     tactics
    0.19
     technique
    0.19
     manipulate
    0.19
    æĵį
    0.17
    Activations Density 0.151%

    No Known Activations