© 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 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. 57500
    Prev
    Next
    INDEX
    Explanations

    providing

    np_max-act · gemini-2.0-flash

    This neuron fires on concluding or summary phrases that introduce the main findings (e.g., “In conclusion,” “Taken together,” “Our study shows”) in scientific abstracts.

    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
    PLAY
    -0.07
    �始化
    -0.07
    arseille
    -0.06
     reasonably
    -0.06
    enario
    -0.06
    icao
    -0.06
     seedu
    -0.06
    modele
    -0.06
    names
    -0.06
     taper
    -0.06
    POSITIVE LOGITS
     Investments
    0.07
    辺
    0.07
     Gathering
    0.07
     طبي
    0.07
    lette
    0.06
    ,'"
    0.06
     RPM
    0.06
    -caption
    0.06
    ammen
    0.06
    بت
    0.06
    Activations Density 0.059%

    No Known Activations