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. 5403
    Prev
    Next
    INDEX
    Explanations

    /licenses

    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
     PEM
    -0.06
     kurum
    -0.06
     discussed
    -0.06
    bum
    -0.06
    pan
    -0.06
     cheek
    -0.06
     rozs
    -0.06
     Pb
    -0.06
    ها
    -0.06
    ()).
    -0.06
    POSITIVE LOGITS
     beloved
    0.07
     prosecute
    0.06
     ALTER
    0.06
    宗
    0.06
     Religion
    0.06
    歳
    0.06
     اصول
    0.06
     Giant
    0.06
    favorite
    0.06
    负责
    0.06
    Activations Density 0.001%

    No Known Activations