© 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. 18771
    Prev
    Next
    INDEX
    Explanations

    food/recipes/diet

    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
    ibrate
    -0.07
    .sat
    -0.07
    -cover
    -0.07
    IDGE
    -0.07
     clearly
    -0.06
     Duplicate
    -0.06
     brewery
    -0.06
    末
    -0.06
    نین
    -0.06
     chick
    -0.06
    POSITIVE LOGITS
     hod
    0.07
    SHORT
    0.06
     guint
    0.06
     dağı
    0.06
    翻
    0.06
     Als
    0.06
    .sax
    0.06
     Explosion
    0.05
     LOT
    0.05
    	HANDLE
    0.05
    Activations Density 0.026%

    No Known Activations