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. 111653
    Prev
    Next
    INDEX
    Explanations

    are

    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
    	col
    -0.07
     cel
    -0.06
    Subtitle
    -0.06
    (other
    -0.06
    	base
    -0.06
     ith
    -0.06
    	input
    -0.06
    .padding
    -0.06
    ид
    -0.06
     timed
    -0.06
    POSITIVE LOGITS
     предпоч
    0.07
     म
    0.06
    //===
    0.06
     والم
    0.06
     Cousins
    0.06
     itinerary
    0.06
    เม
    0.06
    ηρε
    0.06
     Tribunal
    0.06
     gamers
    0.06
    Activations Density 0.001%

    No Known Activations