© 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. 27-RESID-POST-AA
    11. 102567
    Prev
    Next
    INDEX
    Explanations

    "Vis" and variants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XElement
    -0.07
    Generate
    -0.07
    UseProgram
    -0.06
    	idx
    -0.06
     inherit
    -0.06
     “[
    -0.06
    marginLeft
    -0.06
    	connection
    -0.06
    現在
    -0.06
    hoe
    -0.06
    POSITIVE LOGITS
     has
    0.06
    spi
    0.06
     sinful
    0.06
     confronting
    0.06
     acesso
    0.06
    ■■
    0.06
    _tiles
    0.06
     رسم
    0.06
     Puppy
    0.06
    COM
    0.06
    Activations Density 0.059%

    No Known Activations