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. 110638
    Prev
    Next
    INDEX
    Explanations

    the

    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
     poj
    -0.07
     cosa
    -0.07
     [],
    ↵
    -0.06
    Numbers
    -0.06
    ']))
    ↵
    -0.06
     nga
    -0.06
    Mean
    -0.06
    }`}↵
    -0.06
    INCLUDE
    -0.06
     quat
    -0.06
    POSITIVE LOGITS
    官网
    0.07
     دولت
    0.06
     милли
    0.06
    /io
    0.06
     різних
    0.06
     mildly
    0.06
    重大
    0.06
    �다
    0.06
     Patt
    0.06
    唯一
    0.06
    Activations Density 0.001%

    No Known Activations