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

    Neuronpedia

    Jacobian LensNEW
    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. 38198
    Prev
    Next
    INDEX
    Explanations

    Complaints/Issues

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of payments or monetary transactions.

    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
     bishops
    -0.08
     film
    -0.06
    sut
    -0.06
    Hints
    -0.06
    -li
    -0.06
    พล
    -0.06
    Jobs
    -0.06
    uess
    -0.06
    aned
    -0.05
    leared
    -0.05
    POSITIVE LOGITS
     MAG
    0.07
     COS
    0.06
    	copy
    0.06
     고
    0.06
    visející
    0.06
     Receiver
    0.06
    (texture
    0.06
     З
    0.06
     Regional
    0.06
     GUILayout
    0.06
    Activations Density 0.099%

    No Known Activations