© 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. 72162
    Prev
    Next
    INDEX
    Explanations

    finance

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of financial sponsors or investors—especially private equity firms and capital‐group names—in M&A contexts.

    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
    CAA
    -0.07
     interpolation
    -0.07
     refr
    -0.06
    agn
    -0.06
     cloned
    -0.06
    ne
    -0.06
    pull
    -0.06
    SEP
    -0.06
    change
    -0.06
    cbc
    -0.06
    POSITIVE LOGITS
     욕
    0.08
     COS
    0.07
    Approved
    0.06
     congress
    0.06
     تع
    0.06
    >Loading
    0.06
     patriotism
    0.06
    JSONException
    0.06
     تصویر
    0.06
    _EXECUTE
    0.06
    Activations Density 0.008%

    No Known Activations