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. 112652
    Prev
    Next
    INDEX
    Explanations

    type

    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
    Dims
    -0.07
    สว
    -0.06
     Crushers
    -0.06
     towering
    -0.06
     bajo
    -0.06
     ترین
    -0.06
     conectar
    -0.06
     Văn
    -0.06
     новых
    -0.06
     Vũ
    -0.06
    POSITIVE LOGITS
    _.
    0.07
    $type
    0.07
    "(
    0.07
    ']=='
    0.07
     inlet
    0.07
     confronted
    0.06
     reactive
    0.06
    >`↵
    0.06
    >";↵
    0.06
     tipo
    0.06
    Activations Density 0.025%

    No Known Activations