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. 94182
    Prev
    Next
    INDEX
    Explanations

    startup

    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
     ignorance
    -0.07
    目录
    -0.07
     sene
    -0.06
    erer
    -0.06
     Chlor
    -0.06
     liquor
    -0.06
     Cler
    -0.06
     Ble
    -0.06
    ()
    ↵
    ↵
    -0.06
     sacram
    -0.06
    POSITIVE LOGITS
     startups
    0.11
     startup
    0.09
     Startup
    0.08
    737
    0.07
    ups
    0.07
     Breitbart
    0.07
     股
    0.06
     Midnight
    0.06
     nově
    0.06
     jedna
    0.06
    Activations Density 0.007%

    No Known Activations