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. 15-RESID-POST-AA
    6. 105760
    Prev
    Next
    INDEX
    Explanations

    lamin

    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
    ....
    -0.07
     πολ
    -0.07
    adla
    -0.07
    ITTLE
    -0.06
    	obj
    -0.06
     sockfd
    -0.06
    $obj
    -0.06
    (sql
    -0.06
    fuck
    -0.06
     aktiv
    -0.06
    POSITIVE LOGITS
     dedicate
    0.07
     lamin
    0.06
     metadata
    0.06
     glamorous
    0.06
     Manning
    0.06
    affe
    0.06
    Permanent
    0.06
     TForm
    0.06
     laminate
    0.06
    Oper
    0.06
    Activations Density 0.004%

    No Known Activations