© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129753
    Prev
    Next
    INDEX
    Explanations

    /bash

    np_max-act · gemini-2.0-flash

    This neuron activates on the shebang or interpreter path for Bash scripts (e.g. “#!/bin/bash”).

    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
    Lord
    -0.07
     Lok
    -0.06
     parse
    -0.06
    ête
    -0.06
     Lord
    -0.06
     invade
    -0.06
    Ngày
    -0.06
     André
    -0.06
     hôm
    -0.06
    ipc
    -0.06
    POSITIVE LOGITS
    ,以及
    0.07
    ับ
    0.06
    導
    0.06
     basın
    0.06
     ancient
    0.06
     adec
    0.06
    929
    0.06
     aVar
    0.06
     издел
    0.06
    -resolution
    0.06
    Activations Density 0.001%

    No Known Activations