© 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. 7-RESID-POST-AA
    6. 98196
    Prev
    Next
    INDEX
    Explanations

    bypass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Unreal
    -0.07
    陵
    -0.06
    paths
    -0.06
    励
    -0.06
     alleviate
    -0.06
    어
    -0.06
    yalty
    -0.06
     penned
    -0.06
    lou
    -0.05
    	ep
    -0.05
    POSITIVE LOGITS
     carrying
    0.07
     BuzzFeed
    0.07
     куб
    0.07
    MetaData
    0.06
     controversial
    0.06
    .RowIndex
    0.06
     retro
    0.06
    \">\
    0.06
     patriotic
    0.06
    Bush
    0.06
    Activations Density 0.001%

    No Known Activations