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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130786
    Prev
    Next
    INDEX
    Explanations

    store

    np_max-act · gemini-2.0-flash

    This neuron primarily triggers on code references to a “store” (e.g. import statements, props, or variable names containing “store”).

    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
    вай
    -0.07
    ruise
    -0.06
    efd
    -0.06
    WISE
    -0.06
    YW
    -0.06
    	events
    -0.06
     Raleigh
    -0.06
     praised
    -0.06
    	call
    -0.06
    sets
    -0.06
    POSITIVE LOGITS
    ือ
    0.07
     také
    0.06
     Mosul
    0.06
     ayuda
    0.06
    /Observable
    0.06
     BLL
    0.06
    队
    0.06
    �
    0.06
     Transaction
    0.06
    _BUSY
    0.06
    Activations Density 0.006%

    No Known Activations