© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 37702
    Prev
    Next
    INDEX
    Explanations

    Code snippets or formulas

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     problemas
    -0.07
    "/>
↵
    -0.06
    Arrow
    -0.06
    	mem
    -0.06
    .That
    -0.06
    Uploaded
    -0.06
    Cards
    -0.06
     Fecha
    -0.06
     cher
    -0.06
     рек
    -0.06
    POSITIVE LOGITS
    .multi
    0.07
     agree
    0.06
    	payload
    0.06
    traction
    0.06
    不同
    0.06
     shampoo
    0.06
     Pull
    0.06
    .off
    0.06
     �
    0.06
    coin
    0.06
    Activations Density 0.001%

    No Known Activations