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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56102
    Prev
    Next
    INDEX
    Explanations

    trick

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “trick” (often in contexts offering tips or tricks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مطالعه
    -0.07
     sustainable
    -0.07
     Esther
    -0.07
    -European
    -0.07
     Continent
    -0.06
     मह
    -0.06
     клу
    -0.06
     judgement
    -0.06
    eneration
    -0.06
    Coverage
    -0.06
    POSITIVE LOGITS
     trick
    0.14
     Trick
    0.11
     tricks
    0.11
     tricky
    0.10
     Tricks
    0.10
    ımı
    0.07
     Circus
    0.07
     trouble
    0.07
     Heck
    0.07
    Class
    0.07
    Activations Density 0.005%

    No Known Activations