© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 92510
    Prev
    Next
    INDEX
    Explanations

    whether

    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
     plainly
    -0.07
     Ft
    -0.07
    -ft
    -0.07
    .as
    -0.07
     Dj
    -0.06
     ow
    -0.06
    pec
    -0.06
    sr
    -0.06
     Easy
    -0.06
     FORMAT
    -0.06
    POSITIVE LOGITS
    arf
    0.07
    。',↵
    0.06
    抓
    0.06
     ابراه
    0.06
     MatButtonModule
    0.06
    oolStrip
    0.06
    组织
    0.06
    {},↵
    0.06
    راف
    0.06
    ديث
    0.05
    Activations Density 0.013%

    No Known Activations