© 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. 65228
    Prev
    Next
    INDEX
    Explanations

    cheaper

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical tokens and numeric values (e.g., digits, measurements, durations).

    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
     rainy
    -0.06
    γκό
    -0.06
    移动
    -0.06
    mongoose
    -0.06
     wards
    -0.06
     revel
    -0.06
    ニニ
    -0.06
    licative
    -0.05
    Yaw
    -0.05
    .mat
    -0.05
    POSITIVE LOGITS
    .Group
    0.07
     systém
    0.07
     técn
    0.07
     Printable
    0.06
    社会
    0.06
     abc
    0.06
    lore
    0.06
    (ext
    0.06
     очеред
    0.06
     ens
    0.06
    Activations Density 0.442%

    No Known Activations