Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 97614
    Prev
    Next
    INDEX
    Explanations

    ,

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرسمي
    -0.06
    addons
    -0.06
    jej
    -0.06
     рав
    -0.06
     connexion
    -0.06
     sigue
    -0.06
    admin
    -0.06
     mail
    -0.06
    _SCL
    -0.06
    manager
    -0.05
    POSITIVE LOGITS
     删除
    0.06
    _Runtime
    0.06
     landscaping
    0.06
    Ř
    0.06
     выращи
    0.06
    //{↵
    0.06
    .ActionEvent
    0.06
    UsageId
    0.06
     レ
    0.06
     üzerinden
    0.06
    Activations Density 0.293%

    No Known Activations