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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 29709
    Prev
    Next
    INDEX
    Explanations

    scientific data

    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
     franchise
    -0.07
    	selected
    -0.06
     cocci
    -0.06
     predecessors
    -0.06
    าคา
    -0.06
     đích
    -0.06
     visual
    -0.06
     léč
    -0.06
    Effects
    -0.06
    _RUNNING
    -0.06
    POSITIVE LOGITS
    .LEADING
    0.07
     sebou
    0.07
    :[],↵
    0.07
    ú
    0.06
     reliant
    0.06
     repost
    0.06
    _EQ
    0.06
    ̧
    0.06
    ικό
    0.06
    Ѕ
    0.06
    Activations Density 0.019%

    No Known Activations