© 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. 57760
    Prev
    Next
    INDEX
    Explanations

    Today

    np_max-act · gemini-2.0-flash

    This neuron fires on the discourse marker “Today,” (i.e. the word “Today” used to introduce or timestamp a statement).

    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
    EAR
    -0.07
    械
    -0.06
     Charter
    -0.06
    -Д
    -0.06
    vro
    -0.06
    Tap
    -0.06
    xda
    -0.06
    _allocated
    -0.06
     Thames
    -0.06
    azines
    -0.06
    POSITIVE LOGITS
     today
    0.10
    Today
    0.09
     Today
    0.08
     Serve
    0.07
    .Today
    0.06
     Day
    0.06
     shells
    0.06
    _slave
    0.06
    =''
    0.06
    %;
    0.06
    Activations Density 0.034%

    No Known Activations