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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 102304
    Prev
    Next
    INDEX
    Explanations

    monitor

    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
     Decoration
    -0.07
     Pru
    -0.07
    camel
    -0.07
     Blue
    -0.07
    _WARNING
    -0.07
    घ
    -0.07
     NAS
    -0.07
    ань
    -0.06
    medical
    -0.06
    Protect
    -0.06
    POSITIVE LOGITS
     pres
    0.06
     تنظیم
    0.06
     trouble
    0.06
    ElapsedTime
    0.06
     MessageBox
    0.06
     '%$
    0.06
    strict
    0.06
     приб
    0.06
    .localtime
    0.06
    ONGO
    0.06
    Activations Density 0.023%

    No Known Activations