© 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. 27-RESID-POST-AA
    11. 102771
    Prev
    Next
    INDEX
    Explanations

    мы

    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
    Not in Any Lists

    No Comments

    Negative Logits
    =P
    -0.07
     V
    -0.06
     containers
    -0.06
     P
    -0.06
     harm
    -0.06
     dạy
    -0.06
    List
    -0.06
    acro
    -0.06
     companyId
    -0.06
     Sounds
    -0.06
    POSITIVE LOGITS
    /mail
    0.07
    나요
    0.07
    aina
    0.07
     cig
    0.06
    Hospital
    0.06
    舍
    0.06
    isiyle
    0.06
    줄
    0.06
    django
    0.06
    езд
    0.06
    Activations Density 0.006%

    No Known Activations