© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41620
    Prev
    Next
    INDEX
    Explanations

    ridiculous, silly, stupid, incoherent

    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
     careless
    -0.12
    izr
    -0.10
     compl
    -0.10
     horror
    -0.10
    istr
    -0.09
     irresponsible
    -0.09
     freak
    -0.09
     incompetence
    -0.09
     undes
    -0.09
     gre
    -0.09
    POSITIVE LOGITS
     Rid
    0.26
    rid
    0.23
     ridiculous
    0.23
     silly
    0.22
     RID
    0.22
    èįĴ
    0.21
     nons
    0.21
     rid
    0.19
     stupid
    0.18
    upid
    0.18
    Activations Density 0.134%

    No Known Activations