© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 73265
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    (DWORD
    -0.06
    」，
    -0.06
     infused
    -0.06
    92
    -0.06
     مستق
    -0.06
    "}}↵
    -0.06
    Sector
    -0.05
    969
    -0.05
    	des
    -0.05
    .UN
    -0.05
    POSITIVE LOGITS
    TableView
    0.07
    iership
    0.07
    طب
    0.07
     tươi
    0.07
    atted
    0.06
    ━━━━
    0.06
     Peaks
    0.06
    ENTICATION
    0.06
    bulk
    0.06
     Backbone
    0.06
    Activations Density 0.052%

    No Known Activations