© 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. 85805
    Prev
    Next
    INDEX
    Explanations

    subject

    np_max-act · gemini-2.0-flash

    The neuron detects words from the license‐header comment block (e.g. copyright/license boilerplate text).

    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
    .Views
    -0.06
    STER
    -0.06
     Phone
    -0.06
    ิน
    -0.06
     iOS
    -0.06
    Ster
    -0.06
    ierung
    -0.06
     surrounded
    -0.06
     klient
    -0.06
    (desc
    -0.06
    POSITIVE LOGITS
     disappointing
    0.07
     nond
    0.07
     equity
    0.07
     şik
    0.07
    	contentPane
    0.07
     illuminated
    0.06
    .getSelectedItem
    0.06
    益
    0.06
    ,void
    0.06
    ,"↵
    0.06
    Activations Density 0.002%

    No Known Activations