© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8799
    Prev
    Next
    INDEX
    Explanations

    MODULE

    np_max-act · gemini-2.0-flash

    This neuron activates on Linux kernel module metadata macros and declarations (e.g. MODULE_AUTHOR, MODULE_DESCRIPTION, MODULE_LICENSE, module_param).

    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
    ประถม
    -0.07
    Hay
    -0.07
    .Ad
    -0.06
    Pat
    -0.06
    _Count
    -0.06
    γμα
    -0.06
     pyt
    -0.06
    _period
    -0.06
    -validator
    -0.06
    kovou
    -0.06
    POSITIVE LOGITS
     Methods
    0.06
     nằm
    0.06
    -minus
    0.06
     troub
    0.06
     axial
    0.06
     WITHOUT
    0.06
     underground
    0.06
    -me
    0.06
    产生
    0.06
     makes
    0.06
    Activations Density 0.001%

    No Known Activations