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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 53716
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/code

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _prec
    -0.07
     overpower
    -0.06
     आए
    -0.06
     mL
    -0.06
    _preference
    -0.06
     mái
    -0.06
    mant
    -0.06
    Utility
    -0.06
     antic
    -0.06
    (크기
    -0.06
    POSITIVE LOGITS
     dataGridViewTextBoxColumn
    0.07
    řel
    0.07
    .KEY
    0.06
    inci
    0.06
    eworld
    0.06
     정치
    0.06
     hiệu
    0.06
     最
    0.06
    live
    0.06
    抑
    0.06
    Activations Density 0.017%

    No Known Activations