© 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. 56512
    Prev
    Next
    INDEX
    Explanations

    blending

    np_max-act · gemini-2.0-flash

    The neuron activates on words that describe mixing or combining elements—e.g. “blend,” “merge,” “combine,” and “mix.”

    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
    .W
    -0.07
    .False
    -0.07
     BehaviorSubject
    -0.06
     indicates
    -0.06
     Yah
    -0.06
     Calculate
    -0.06
     clientes
    -0.06
    aeda
    -0.06
    .HCM
    -0.06
     frec
    -0.06
    POSITIVE LOGITS
     combines
    0.07
    -sex
    0.07
    mez
    0.06
     athleticism
    0.06
    -HT
    0.06
     mix
    0.06
    UME
    0.06
     диаг
    0.06
    _race
    0.06
    Race
    0.06
    Activations Density 0.030%

    No Known Activations