© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130249
    Prev
    Next
    INDEX
    Explanations

    .Scanner

    np_max-act · gemini-2.0-flash

    The neuron fires on Java input/output constructs—especially Scanner declarations and uses of System.in (.nextInt, .nextLine) and similar I/O calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     αξ
    -0.06
     Applicants
    -0.06
     chẳng
    -0.06
     pictures
    -0.06
    AQ
    -0.06
    Bang
    -0.06
    HERE
    -0.06
    /fl
    -0.06
     refs
    -0.06
    .Touch
    -0.06
    POSITIVE LOGITS
    เธอ
    0.07
    _INFO
    0.07
     mozilla
    0.07
     заболевания
    0.06
    .FileSystem
    0.06
    	InputStream
    0.06
    imming
    0.06
    _DRAW
    0.06
    iphers
    0.06
    <\/
    0.06
    Activations Density 0.001%

    No Known Activations