© 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. 60439
    Prev
    Next
    INDEX
    Explanations

    {

    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
    .to
    -0.07
    -or
    -0.06
     hood
    -0.06
    oltage
    -0.06
     mundial
    -0.06
    ніх
    -0.06
     Alo
    -0.06
     UIWindow
    -0.06
     Defender
    -0.06
     '}↵
    -0.06
    POSITIVE LOGITS
     {
    0.10
    ulist
    0.10
    |
    0.07
     lyric
    0.07
    {//
    0.07
    '){
    0.06
    :CGPoint
    0.06
     ){
    0.06
    Paris
    0.06
    IMPLEMENT
    0.06
    Activations Density 0.017%

    No Known Activations