© 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. 7323
    Prev
    Next
    INDEX
    Explanations

    dry

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “virtual background” (and closely related tutorial contexts about adding or using virtual backgrounds).

    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
    inciple
    -0.06
     PLUS
    -0.06
     Collection
    -0.05
     drew
    -0.05
     Submit
    -0.05
     focusing
    -0.05
    Tv
    -0.05
    pole
    -0.05
     robes
    -0.05
     Explosion
    -0.05
    POSITIVE LOGITS
    (COM
    0.07
    _now
    0.07
    aniem
    0.07
    ี.
    0.06
     Maced
    0.06
    htt
    0.06
     getInt
    0.06
    iffies
    0.06
    vál
    0.06
    unitOfWork
    0.06
    Activations Density 0.235%

    No Known Activations