© 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. 11-RESID-POST-AA
    11. 27567
    Prev
    Next
    INDEX
    Explanations

    .R

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     APP
    -0.07
     erect
    -0.07
     dor
    -0.06
     ST
    -0.06
     Administrative
    -0.06
     Kar
    -0.06
     St
    -0.06
     Quang
    -0.06
     mužů
    -0.06
    /****************************************
    -0.06
    POSITIVE LOGITS
     }()↵
    0.07
    (Sender
    0.06
    ระด
    0.06
    gL
    0.06
    stash
    0.06
    快速
    0.06
    κολ
    0.06
     내용
    0.06
    uitar
    0.06
    genres
    0.06
    Activations Density 0.001%

    No Known Activations