© 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
    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. 54473
    Prev
    Next
    INDEX
    Explanations

    parts of something

    np_max-act · gemini-2.0-flash

    This neuron activates on placeholder tokens combining a label like “NAME” with an underscore and a digit (e.g. “NAME_1”, “NAME_2”, “NAME_3”).

    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
    683
    -0.07
    結
    -0.06
    ailure
    -0.06
    -д
    -0.06
    .Style
    -0.06
    763
    -0.06
     Cuomo
    -0.06
    род
    -0.06
     現
    -0.06
    ÔNG
    -0.06
    POSITIVE LOGITS
    илась
    0.07
    Installer
    0.07
     pissed
    0.07
    ampton
    0.07
     isEmpty
    0.06
    amt
    0.06
    .isDebugEnabled
    0.06
     siden
    0.06
    GameManager
    0.06
    uy
    0.06
    Activations Density 0.356%

    No Known Activations