© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 59194
    Prev
    Next
    INDEX
    Explanations

    android

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TLabel
    -0.06
     Schwar
    -0.06
    γραμμα
    -0.06
     ตาม
    -0.06
     dane
    -0.06
     어떻게
    -0.06
     Fear
    -0.06
    tout
    -0.06
    atég
    -0.06
    468
    -0.06
    POSITIVE LOGITS
     miss
    0.06
    Speech
    0.06
     emotionally
    0.06
     beds
    0.06
    /s
    0.06
     android
    0.06
    Audio
    0.06
    AccessException
    0.06
     Salvador
    0.06
    은
    0.06
    Activations Density 0.005%

    No Known Activations