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. 15-RESID-POST-AA
    6. 84356
    Prev
    Next
    INDEX
    Explanations

    of

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inaccur
    -0.06
    етич
    -0.06
    jeme
    -0.06
    Boundary
    -0.06
    lü
    -0.06
     setLocation
    -0.06
    	Route
    -0.06
    แผ
    -0.06
     �
    -0.06
    osit
    -0.06
    POSITIVE LOGITS
    úng
    0.07
     addItem
    0.07
     awkward
    0.06
    weeted
    0.06
     yardım
    0.06
     chac
    0.06
    …↵
    0.06
     -*-
    0.06
    Ó
    0.06
     mohla
    0.06
    Activations Density 0.165%

    No Known Activations