© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 30719
    Prev
    Next
    INDEX
    Explanations

    Source

    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
    乐
    -0.06
    조
    -0.06
    (images
    -0.06
    /storage
    -0.06
    .published
    -0.06
    合
    -0.06
     apis
    -0.06
     Row
    -0.06
    .pem
    -0.06
     ON
    -0.06
    POSITIVE LOGITS
     içine
    0.07
     TextFormField
    0.07
    KindOfClass
    0.07
    џџџ
    0.07
    '))↵↵↵
    0.06
    。そして
    0.06
    同时
    0.06
     왔
    0.06
    (jq
    0.06
    ((&___
    0.06
    Activations Density 0.001%

    No Known Activations