© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124833
    Prev
    Next
    INDEX
    Explanations

    online posts/comments

    np_max-act · gemini-2.0-flash

    This neuron fires on fragments of external resource references (URLs and link identifiers).

    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
     Tell
    -0.07
    析
    -0.06
     tracker
    -0.06
    -Free
    -0.06
    UCK
    -0.06
     trackers
    -0.06
    AKE
    -0.06
     router
    -0.06
    其他
    -0.06
    	el
    -0.06
    POSITIVE LOGITS
     вищ
    0.08
     turist
    0.07
     Yo
    0.07
     Για
    0.06
    (':',
    0.06
    ruž
    0.06
    ุรก
    0.06
     앉
    0.06
     zk
    0.06
                   ↵
    0.06
    Activations Density 0.048%

    No Known Activations