© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59395
    Prev
    Next
    INDEX
    Explanations

    electric

    np_max-act · gemini-2.0-flash

    This neuron responds to references to electricity and electric phenomena (e.g., words like “electric,” “shocking,” “voltage,” “electrophorus,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    .ToolStripItem
    -0.07
    amed
    -0.07
     concatenated
    -0.07
    韩
    -0.07
    BOUND
    -0.06
     Salah
    -0.06
     lor
    -0.06
    izational
    -0.06
     totalement
    -0.06
     inplace
    -0.06
    POSITIVE LOGITS
    No
    0.06
    NK
    0.06
    PMC
    0.06
    .visit
    0.06
    ньої
    0.06
     Nashville
    0.06
    intosh
    0.06
     stalo
    0.06
    It
    0.06
     defy
    0.05
    Activations Density 0.022%

    No Known Activations