© 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. 108920
    Prev
    Next
    INDEX
    Explanations

    effects

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the word “Effects” (and nearby tokens) when it appears as the heading or lead‐in to describe a study’s focus.

    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
     приз
    -0.06
     bunny
    -0.06
     underwear
    -0.06
    iado
    -0.06
    else
    -0.06
     sergeant
    -0.06
     vrij
    -0.06
    perl
    -0.06
    .indent
    -0.06
     boil
    -0.06
    POSITIVE LOGITS
     Nachricht
    0.07
     jTextField
    0.06
     nuevo
    0.06
    اضی
    0.06
     effects
    0.06
    /_
    0.06
     yönetimi
    0.06
     prompting
    0.06
     sost
    0.06
    olor
    0.06
    Activations Density 0.020%

    No Known Activations