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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 89078
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    np_max-act · gemini-2.0-flash

    The neuron activates on numbered list markers (the digits “1” through “10” that introduce each item in an enumerated list).

    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
    -all
    -0.08
    �
    -0.07
    -show
    -0.07
     gốc
    -0.07
    -priced
    -0.06
     paramString
    -0.06
    crm
    -0.06
    -mounted
    -0.06
    (nil
    -0.06
     объект
    -0.06
    POSITIVE LOGITS
    บาล
    0.06
    AUT
    0.06
     वजह
    0.06
    .hostname
    0.06
    Converter
    0.06
     believer
    0.06
     DISCLAIMED
    0.06
    .BatchNorm
    0.06
    Pal
    0.06
    etro
    0.06
    Activations Density 0.103%

    No Known Activations