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. 110600
    Prev
    Next
    INDEX
    Explanations

    more

    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
     thuộc
    -0.08
     humano
    -0.07
     consenting
    -0.07
     Kirk
    -0.07
     hệ
    -0.07
    DIM
    -0.07
    _preference
    -0.07
    Bow
    -0.07
    臺灣
    -0.07
    Dan
    -0.06
    POSITIVE LOGITS
     INTER
    0.06
    _TRANSACTION
    0.06
    亮
    0.06
     scrapped
    0.06
     Marxism
    0.05
     interior
    0.05
     ADMIN
    0.05
    Header
    0.05
    context
    0.05
    약
    0.05
    Activations Density 0.000%

    No Known Activations