© 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. 89371
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects calls to output or logging methods (e.g. System.out.println and similar print/log statements).

    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
    .dx
    -0.08
     host
    -0.07
     hazards
    -0.07
     Layout
    -0.07
    _contents
    -0.07
    .conf
    -0.06
     DX
    -0.06
    .py
    -0.06
    fuse
    -0.06
    /rand
    -0.06
    POSITIVE LOGITS
    ứ
    0.07
    答案
    0.06
    -drive
    0.06
    ––
    0.06
     pregnancy
    0.06
    ,,,
    0.06
     getLocation
    0.06
     Sleeve
    0.06
     составляет
    0.06
     exercitation
    0.06
    Activations Density 0.024%

    No Known Activations