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. 83970
    Prev
    Next
    INDEX
    Explanations

    punctuation: comma

    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
     Asking
    -0.07
     Objects
    -0.07
    ))↵
    -0.07
     बड़
    -0.06
    	help
    -0.06
     More
    -0.06
     genitals
    -0.06
    auce
    -0.06
    jin
    -0.06
    lots
    -0.06
    POSITIVE LOGITS
    atrix
    0.06
    INT
    0.06
    \GeneratedValue
    0.06
    :@
    0.06
    (bundle
    0.06
    _Client
    0.06
    PERATURE
    0.06
    xic
    0.06
    USR
    0.06
    andExpect
    0.06
    Activations Density 0.001%

    No Known Activations