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. 19-RESID-POST-AA
    6. 9816
    Prev
    Next
    INDEX
    Explanations

    code

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otes
    -0.06
    otal
    -0.06
    に見
    -0.06
     Bil
    -0.06
     harming
    -0.06
    ("{}
    -0.06
     уровне
    -0.06
    ská
    -0.06
     pioneered
    -0.06
    501
    -0.06
    POSITIVE LOGITS
    ครงการ
    0.07
    Expired
    0.07
     chặt
    0.07
     pancakes
    0.06
    -Assad
    0.06
     spiele
    0.06
     asynchronous
    0.06
     mastered
    0.06
    .DataBindings
    0.06
    ınızı
    0.06
    Activations Density 0.040%

    No Known Activations