© 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. 109858
    Prev
    Next
    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “want” (and closely related “to want” constructs), signaling expressions of desire or requests.

    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
    (image
    -0.07
    edian
    -0.07
    ентами
    -0.07
    |()↵
    -0.06
    anium
    -0.06
     plataforma
    -0.06
    aramel
    -0.06
     mariage
    -0.06
    Senate
    -0.06
    _usuario
    -0.06
    POSITIVE LOGITS
    	Config
    0.06
     unterschied
    0.06
    ุญาต
    0.06
    最高
    0.06
     Refer
    0.06
     design
    0.06
     Shard
    0.06
    (acc
    0.06
    (action
    0.06
     intimidating
    0.06
    Activations Density 0.017%

    No Known Activations