© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93999
    Prev
    Next
    INDEX
    Explanations

    Kim

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nah
    -0.06
    169
    -0.06
    .cz
    -0.06
    ulle
    -0.06
     hazır
    -0.06
    173
    -0.06
     흔
    -0.06
    />
    -0.06
     查
    -0.06
    	Gtk
    -0.05
    POSITIVE LOGITS
     Kim
    0.39
    Kim
    0.32
     kim
    0.21
    kim
    0.14
     Kimberly
    0.11
     金
    0.10
     김
    0.09
     kims
    0.09
    金
    0.09
    김
    0.08
    Activations Density 0.003%

    No Known Activations