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. 69711
    Prev
    Next
    INDEX
    Explanations

    areas

    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
    Women
    -0.06
     demeanor
    -0.06
     holder
    -0.06
    (tx
    -0.06
     tolerance
    -0.06
     Operators
    -0.06
     prem
    -0.06
    уванні
    -0.06
    ीटर
    -0.06
     elm
    -0.06
    POSITIVE LOGITS
    اط
    0.07
     나라
    0.07
     Tory
    0.06
    کت
    0.06
    	Json
    0.06
    Ass
    0.06
     fearless
    0.06
    ợ
    0.06
     И
    0.06
    -lib
    0.06
    Activations Density 0.158%

    No Known Activations