© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55528
    Prev
    Next
    INDEX
    Explanations

    sell

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect the word “sell” (and its inflected form “selling”).

    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
    uggest
    -0.08
     İmpar
    -0.07
     refuge
    -0.07
    .groupControl
    -0.07
    遗
    -0.07
     appreh
    -0.06
     observer
    -0.06
    pectrum
    -0.06
    perience
    -0.06
    -focus
    -0.06
    POSITIVE LOGITS
     sell
    0.16
     sold
    0.13
     selling
    0.11
     Sold
    0.11
     SOLD
    0.11
     sellers
    0.11
     Sale
    0.10
     seller
    0.10
     sale
    0.10
     sells
    0.10
    Activations Density 0.036%

    No Known Activations