© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 105389
    Prev
    Next
    INDEX
    Explanations

    signal

    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
    ペ
    -0.07
    words
    -0.07
     speeches
    -0.07
     patt
    -0.07
    peek
    -0.07
    ccion
    -0.07
     obt
    -0.07
    _LT
    -0.06
     ClassName
    -0.06
     lep
    -0.06
    POSITIVE LOGITS
    .switch
    0.06
    ังก
    0.06
     разработ
    0.06
     //////////
    0.06
     할인
    0.06
    reeze
    0.06
     Ethan
    0.06
    칙
    0.06
    _vert
    0.06
     ViewModel
    0.06
    Activations Density 0.020%

    No Known Activations