© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30025
    Prev
    Next
    INDEX
    Explanations

    services and technical documents

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on finance/trading jargon and abbreviations (e.g. NPV, Post-Trade, FX, PT reporting, LEI, Kafka clusters).

    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
    melon
    -0.07
    facet
    -0.07
     Uganda
    -0.06
     IX
    -0.06
    _latitude
    -0.06
    Conta
    -0.06
     suche
    -0.06
    �
    -0.06
    _mtx
    -0.06
    Cog
    -0.06
    POSITIVE LOGITS
     shaken
    0.07
    htm
    0.07
     battleground
    0.06
    _UD
    0.06
    displayName
    0.06
    ครง
    0.06
     Rout
    0.06
    _losses
    0.06
     tấn
    0.06
    аб
    0.06
    Activations Density 0.098%

    No Known Activations