© 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. 128408
    Prev
    Next
    INDEX
    Explanations

    polym

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the substring “polym” (as in polymorphism or polymorphic) in genetic‐variation contexts.

    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
     arena
    -0.07
    +c
    -0.07
    redicate
    -0.07
     Twitter
    -0.07
     DataSet
    -0.06
     shred
    -0.06
     Acres
    -0.06
     Translator
    -0.06
    _callback
    -0.06
     astronaut
    -0.06
    POSITIVE LOGITS
    रल
    0.08
     ""),
    0.07
    ‌تر
    0.07
    .options
    0.06
     YM
    0.06
     болез
    0.06
     RCMP
    0.06
     �
    0.06
    IW
    0.06
    、小
    0.06
    Activations Density 0.002%

    No Known Activations