© 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. 11-RESID-POST-AA
    6. 76827
    Prev
    Next
    INDEX
    Explanations

    website/site

    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
    icycle
    -0.07
    posite
    -0.07
    /c
    -0.07
    ([[
    -0.06
     finest
    -0.06
    Options
    -0.06
     basin
    -0.06
    区
    -0.06
    _CHANNELS
    -0.06
    Alloc
    -0.06
    POSITIVE LOGITS
      ↵↵
    0.06
     diseñ
    0.06
     lorem
    0.06
     Symptoms
    0.06
     Pfizer
    0.06
    ,一
    0.06
    เหมาะ
    0.06
    ________________________________
    0.06
     мик
    0.06
     /
    0.05
    Activations Density 0.004%

    No Known Activations