© 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. 5796
    Prev
    Next
    INDEX
    Explanations

    gradation

    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
    izin
    -0.07
     introduction
    -0.07
     volunteered
    -0.06
    рам
    -0.06
     manifested
    -0.06
     Couple
    -0.06
    ivas
    -0.06
     Koch
    -0.06
    ुप
    -0.06
    )=>{↵
    -0.06
    POSITIVE LOGITS
    表情
    0.07
    rat
    0.06
     momento
    0.06
    Creator
    0.06
    reator
    0.06
     mob
    0.06
    patrick
    0.06
    _VO
    0.06
    _ISS
    0.05
    ://'
    0.05
    Activations Density 0.060%

    No Known Activations