© 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. 104695
    Prev
    Next
    INDEX
    Explanations

    that

    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
    asley
    -0.07
    _gift
    -0.07
    _dd
    -0.06
     Rece
    -0.06
     přech
    -0.06
    /OR
    -0.06
    vara
    -0.06
     Rican
    -0.06
     исполн
    -0.06
    Feed
    -0.06
    POSITIVE LOGITS
    /header
    0.07
     Glas
    0.07
     differentiate
    0.06
    �
    0.06
    	anim
    0.06
    toLowerCase
    0.06
     emerges
    0.06
     which
    0.06
     حمل
    0.06
    攻击
    0.06
    Activations Density 0.137%

    No Known Activations