© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 72223
    Prev
    Next
    INDEX
    Explanations

    RTL

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens expressing decimal (floating-point) values.

    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
    release
    -0.06
    elapsed
    -0.06
    _MO
    -0.06
    Alarm
    -0.06
     graduated
    -0.06
    を開
    -0.06
    ladığı
    -0.05
    _TBL
    -0.05
     Combine
    -0.05
    >,</
    -0.05
    POSITIVE LOGITS
    .datasource
    0.07
                                   ↵
    0.07
    kses
    0.07
    nem
    0.07
     tolerated
    0.07
     correctamente
    0.07
    шем
    0.06
    full
    0.06
     vp
    0.06
    554
    0.06
    Activations Density 0.002%

    No Known Activations