© 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. 110392
    Prev
    Next
    INDEX
    Explanations

    cellular data

    np_max-act · gemini-2.0-flash

    The neuron detects references to mobile‐internet connectivity—terms like “mobile,” “hotspot,” “cellular,” “network,” and “internet access.”

    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
    Y
    -0.08
    .fil
    -0.07
     Hamburg
    -0.07
    setter
    -0.07
    vidence
    -0.06
    ژی
    -0.06
     θε
    -0.06
    Forest
    -0.06
     Josh
    -0.06
     Лени
    -0.06
    POSITIVE LOGITS
    -interface
    0.07
     LTE
    0.07
     afirm
    0.07
    -elect
    0.07
    toMatchSnapshot
    0.07
     privile
    0.06
    -world
    0.06
    \Http
    0.06
    ाध
    0.06
    dated
    0.06
    Activations Density 0.012%

    No Known Activations