© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91416
    Prev
    Next
    INDEX
    Explanations

    Greeks

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “hedging” (especially “delta hedging”) or related terms, i.e., it detects mentions of hedging strategies.

    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
     Antony
    -0.07
    にする
    -0.07
     José
    -0.06
     شدند
    -0.06
     Helper
    -0.06
    �
    -0.06
    ugador
    -0.06
     Луч
    -0.06
    '''
    -0.06
    Cole
    -0.06
    POSITIVE LOGITS
     FEMA
    0.08
     craz
    0.07
    omap
    0.07
    .tx
    0.07
     bal
    0.06
     aVar
    0.06
     Ι
    0.06
    �
    0.06
    wealth
    0.06
    	level
    0.06
    Activations Density 0.002%

    No Known Activations