© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43061
    Prev
    Next
    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the word “voice,” especially in contexts about giving or having a voice.

    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
     conceived
    -0.07
     cref
    -0.07
     prin
    -0.06
    ở
    -0.06
     относ
    -0.06
     conceive
    -0.06
     ench
    -0.06
     يونيو
    -0.06
     uzak
    -0.06
     Δε
    -0.06
    POSITIVE LOGITS
    ItemSelectedListener
    0.08
     GroupLayout
    0.07
     双
    0.07
     TextAlign
    0.07
    civil
    0.07
     đàn
    0.07
     amacı
    0.07
    (JSON
    0.06
     piyas
    0.06
    .sap
    0.06
    Activations Density 0.020%

    No Known Activations