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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 111452
    Prev
    Next
    INDEX
    Explanations

    Given

    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
     kolem
    -0.07
    breadcrumbs
    -0.06
    -chan
    -0.06
    FileSync
    -0.06
    -BEGIN
    -0.06
     bekan
    -0.06
    Ģ
    -0.06
    uální
    -0.06
    DISABLE
    -0.06
    GetProperty
    -0.06
    POSITIVE LOGITS
    **(
    0.07
     compr
    0.06
    िकल
    0.06
    配置
    0.06
     neon
    0.06
    .target
    0.06
    abl
    0.06
                                   ↵
    0.06
    迹
    0.06
    lds
    0.06
    Activations Density 0.034%

    No Known Activations