© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126803
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron activates on brand or product names—especially software and website names.

    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
     Spend
    -0.07
    자료
    -0.07
     ड
    -0.06
     điểm
    -0.06
     dependencies
    -0.06
     Staff
    -0.06
    incre
    -0.06
     kk
    -0.06
     wages
    -0.06
    LOYEE
    -0.06
    POSITIVE LOGITS
     UITableViewController
    0.08
     Universidad
    0.06
    /logo
    0.06
    DDevice
    0.06
    vio
    0.06
    setError
    0.06
     Tacoma
    0.06
    Eine
    0.06
    %/
    0.06
    (app
    0.06
    Activations Density 0.061%

    No Known Activations