Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 7632
    Prev
    Next
    INDEX
    Explanations

    ubiquinone/menaquinone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _indexes
    -0.07
    ğın
    -0.07
    -(
    -0.06
     друго
    -0.06
     chod
    -0.06
    Govern
    -0.06
    (Address
    -0.06
    νηση
    -0.06
     impres
    -0.06
    انی
    -0.06
    POSITIVE LOGITS
     cuc
    0.07
    isse
    0.07
     Abdul
    0.06
     줄
    0.06
    imat
    0.06
    utorials
    0.06
     Log
    0.06
     herk
    0.06
     presets
    0.06
     Adapter
    0.06
    Activations Density 0.013%

    No Known Activations