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. 74620
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     aquatic
    -0.06
    richText
    -0.06
     اکتبر
    -0.06
     Statistical
    -0.06
    itu
    -0.06
     toilet
    -0.06
     therapeutic
    -0.06
    Experimental
    -0.06
    Cols
    -0.06
    Modify
    -0.06
    POSITIVE LOGITS
     Inform
    0.06
    剣
    0.06
    ヶ
    0.06
     HG
    0.06
     име
    0.06
     '/'↵
    0.06
    elerine
    0.06
    Furthermore
    0.06
     STAR
    0.06
     seins
    0.06
    Activations Density 0.025%

    No Known Activations