Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1514
    Prev
    Next
    INDEX
    Explanations

    academic/scientific writing

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptions of preparing or engineering superposition states—e.g. passages detailing how a superposition is created or measured.

    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
    onth
    -0.07
    妹
    -0.07
    ें↵
    -0.06
    !;↵
    -0.06
    .Topic
    -0.06
    ev
    -0.06
     pivot
    -0.06
    يين
    -0.06
    Printing
    -0.06
    лова
    -0.06
    POSITIVE LOGITS
    .AddField
    0.06
     ={
    0.06
     Mitsubishi
    0.06
    	TokenName
    0.06
     mult
    0.06
     강
    0.06
     nomine
    0.06
     desks
    0.06
    .mk
    0.06
     Dumpster
    0.06
    Activations Density 0.034%

    No Known Activations