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. 7-RESID-POST-AA
    6. 119325
    Prev
    Next
    INDEX
    Explanations

    p

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*
    -0.07
    *y
    -0.06
     ruining
    -0.06
     침
    -0.06
    ').
    -0.06
    objPHPExcel
    -0.06
    >_
    -0.06
     Implicit
    -0.06
    *L
    -0.06
     flea
    -0.06
    POSITIVE LOGITS
    �
    0.07
    Plugin
    0.07
    �
    0.07
    рещ
    0.06
    	Document
    0.06
     セ
    0.06
    QUIRES
    0.06
    電
    0.06
    organic
    0.06
    246
    0.06
    Activations Density 0.006%

    No Known Activations