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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58799
    Prev
    Next
    INDEX
    Explanations

    Ships being laid down

    np_max-act · gemini-2.0-flash

    This neuron responds to timeline markers—words and numbers indicating dates and the laying-down/launching chronology of a vessel.

    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
    Stan
    -0.07
     Miche
    -0.06
    icc
    -0.06
    "io
    -0.06
     allege
    -0.06
     Mong
    -0.06
    Mongo
    -0.06
     dictatorship
    -0.06
    -out
    -0.05
     monday
    -0.05
    POSITIVE LOGITS
    .LoggerFactory
    0.07
     Other
    0.07
    >(↵
    0.06
     Encode
    0.06
    .UNKNOWN
    0.06
    یم
    0.06
    expense
    0.06
    دیگر
    0.06
    _system
    0.06
    402
    0.06
    Activations Density 0.008%

    No Known Activations