© 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
    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. 13652
    Prev
    Next
    INDEX
    Explanations

    bash

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of shell or system environment variables being set or exported.

    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
    USH
    -0.07
    де
    -0.07
     figured
    -0.06
    .indexOf
    -0.06
     contacted
    -0.06
    ゛
    -0.06
    ,_
    -0.06
    ्ह
    -0.06
    _to
    -0.06
     Mahmoud
    -0.06
    POSITIVE LOGITS
    digest
    0.08
    Refer
    0.06
    }')
    0.06
    輝
    0.06
    ım
    0.06
    othy
    0.06
    patial
    0.06
     Arial
    0.06
    環境
    0.06
    ør
    0.06
    Activations Density 0.003%

    No Known Activations