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. 80159
    Prev
    Next
    INDEX
    Explanations

    article excerpts and comments

    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
     میدان
    -0.06
    zego
    -0.06
    ์ฟ
    -0.06
     услуг
    -0.06
    abela
    -0.06
    zp
    -0.06
    から
    -0.06
    ลาด
    -0.06
     infected
    -0.06
    ksam
    -0.06
    POSITIVE LOGITS
     mitochond
    0.07
    States
    0.07
    保障
    0.07
    _acquire
    0.06
     Brasil
    0.06
    .Sync
    0.06
    .Push
    0.06
    DefaultCellStyle
    0.06
    DECL
    0.06
    =torch
    0.06
    Activations Density 0.130%

    No Known Activations