© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 37877
    Prev
    Next
    INDEX
    Explanations

    steroids and hormones

    np_max-act · gemini-2.0-flash

    This neuron detects subword fragments of biochemical terms—especially those found in steroid and enzyme names (e.g. “hydro,” “xy,” “ol,” “ase”).

    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
     meis
    -0.06
     supper
    -0.06
    しょ
    -0.06
     pessim
    -0.06
     Doom
    -0.06
     believable
    -0.06
    不安
    -0.06
     handicap
    -0.06
    ιβ
    -0.06
     pund
    -0.06
    POSITIVE LOGITS
    Video
    0.07
     evaluate
    0.07
     describe
    0.07
    �
    0.06
     functions
    0.06
     represent
    0.06
     wondering
    0.06
     advance
    0.06
     installation
    0.06
     noreferrer
    0.06
    Activations Density 0.005%

    No Known Activations