© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 54384
    Prev
    Next
    INDEX
    Explanations

    international relations and politics

    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
    ника
    -0.06
     hạ
    -0.06
     sulfur
    -0.06
     जन
    -0.06
     sentencing
    -0.06
    ителя
    -0.06
    ptic
    -0.06
     radiator
    -0.06
     л
    -0.06
    _creation
    -0.05
    POSITIVE LOGITS
     TLabel
    0.08
    Pixel
    0.06
    .FromArgb
    0.06
    OptionsItemSelected
    0.06
    =tk
    0.06
     jpeg
    0.06
     grado
    0.06
    	bs
    0.06
     colorWithRed
    0.06
    olvable
    0.06
    Activations Density 0.013%

    No Known Activations