© 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. 12781
    Prev
    Next
    INDEX
    Explanations

    Army

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is find references to military service (branches, ranks, and service periods).

    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
     Mick
    -0.07
     Katz
    -0.07
     realmente
    -0.06
    bane
    -0.06
    UNT
    -0.06
     basketball
    -0.06
     Vince
    -0.06
    unt
    -0.06
    чки
    -0.06
    ai
    -0.06
    POSITIVE LOGITS
    //
    0.07
    edTextBox
    0.06
     durumlarda
    0.06
    _component
    0.06
     tục
    0.06
     кри
    0.06
     evolving
    0.06
    $num
    0.06
     hatta
    0.06
     reduced
    0.06
    Activations Density 0.018%

    No Known Activations