© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27676
    Prev
    Next
    INDEX
    Explanations

    default

    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
    564
    -0.08
    =DB
    -0.08
    657
    -0.08
    369
    -0.07
     distributed
    -0.07
    posta
    -0.07
    864
    -0.07
    Contains
    -0.07
     offsetX
    -0.06
    овано
    -0.06
    POSITIVE LOGITS
    	back
    0.06
     müda
    0.06
     thí
    0.06
      ↵
    0.06
     viết
    0.06
    ct
    0.06
     fluctuations
    0.06
    ิธ
    0.06
    Fourth
    0.06
     Sym
    0.05
    Activations Density 0.000%

    No Known Activations