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. 99208
    Prev
    Next
    INDEX
    Explanations

    Arial

    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
    FAST
    -0.07
    CHOOL
    -0.07
    ่ำ
    -0.07
     accountant
    -0.06
     Stem
    -0.06
     Jong
    -0.06
     और
    -0.06
    (Xml
    -0.06
     Ade
    -0.06
    ,大
    -0.06
    POSITIVE LOGITS
    �
    0.07
    	exec
    0.06
    DatePicker
    0.06
    ニニ
    0.06
    verter
    0.06
    (EIF
    0.06
    άντα
    0.06
     models
    0.06
    -holder
    0.06
    ussy
    0.06
    Activations Density 0.004%

    No Known Activations