© 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. 9368
    Prev
    Next
    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash

    probability-related questions about picking letters from a set.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates primarily on the word “letters,” i.e. when the text refers to picking or counting “letters.”

    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
    .SE
    -0.07
     Rape
    -0.07
     Seç
    -0.07
     fis
    -0.07
    irection
    -0.06
    +'
    -0.06
     acne
    -0.06
    än
    -0.06
    .Values
    -0.06
     받아
    -0.06
    POSITIVE LOGITS
     Reader
    0.07
     earnings
    0.07
    PET
    0.06
    _log
    0.06
     committing
    0.06
     horas
    0.06
    의
    0.06
     udp
    0.06
    Point
    0.06
     curl
    0.06
    Activations Density 0.001%

    No Known Activations