© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 29914
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    iosa
    -0.06
     IMD
    -0.06
     подав
    -0.06
     ActionController
    -0.06
     Cha
    -0.06
    スク
    -0.06
    яб
    -0.06
     conclusive
    -0.06
     advisable
    -0.06
     defeated
    -0.06
    POSITIVE LOGITS
    usting
    0.08
    WF
    0.07
    ARM
    0.07
    /src
    0.07
    .Design
    0.06
     bold
    0.06
    (ai
    0.06
     Delay
    0.06
    ++)↵
    0.06
     chip
    0.06
    Activations Density 0.116%

    No Known Activations