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. 11-RESID-POST-AA
    6. 100673
    Prev
    Next
    INDEX
    Explanations

    2

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MainActivity
    -0.07
    몰
    -0.07
    อนไลน
    -0.06
    айт
    -0.06
    逐
    -0.06
    �
    -0.06
     Щ
    -0.06
    िए
    -0.06
    ());↵↵↵
    -0.06
    ]:↵
    -0.06
    POSITIVE LOGITS
     bo
    0.07
     prim
    0.07
     responsible
    0.07
     remainder
    0.07
    084
    0.07
     awarded
    0.07
     peak
    0.07
    (profile
    0.07
     incremental
    0.07
    32
    0.07
    Activations Density 0.001%

    No Known Activations