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. 74924
    Prev
    Next
    INDEX
    Explanations

    EU documents

    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
    ٔ
    -0.07
     pře
    -0.06
    .LOG
    -0.06
    ρά
    -0.06
     Cra
    -0.06
     Lưu
    -0.06
     RN
    -0.06
    ,比
    -0.06
    持续
    -0.06
     LIN
    -0.06
    POSITIVE LOGITS
    ;;;;;;;;
    0.06
    act
    0.06
     libro
    0.06
    hg
    0.06
     věd
    0.06
    rimp
    0.06
     ヾ
    0.06
     Visibility
    0.06
    essed
    0.06
     patriotism
    0.05
    Activations Density 0.011%

    No Known Activations