© 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. 27-RESID-POST-AA
    11. 35748
    Prev
    Next
    INDEX
    Explanations

    say "&&"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ktop
    -0.06
     eşit
    -0.06
     putas
    -0.06
    _people
    -0.06
    iOS
    -0.06
    �
    -0.06
     occurrence
    -0.06
    _SQL
    -0.05
     detecting
    -0.05
    	fclose
    -0.05
    POSITIVE LOGITS
     setSupportActionBar
    0.08
    ΕΝ
    0.07
     liaison
    0.07
    .Mail
    0.07
    ,
↵
    0.06
     Matchers
    0.06
    _lang
    0.06
     ABC
    0.06
    028
    0.06
    олева
    0.06
    Activations Density 0.003%

    No Known Activations