© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30185
    Prev
    Next
    INDEX
    Explanations

    buying and selling

    np_max-act · gemini-2.0-flash

    The neuron activates on words relating to buying/selling transactions—terms naming the seller or owner and negotiation cues (buy, sell, price, waiting to hear, offers).

    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
     двер
    -0.07
    уже
    -0.07
     bindActionCreators
    -0.06
    然
    -0.06
    조
    -0.06
    viz
    -0.06
    ayı
    -0.06
     McGregor
    -0.06
    ون
    -0.06
    IED
    -0.06
    POSITIVE LOGITS
    -enh
    0.07
     Solution
    0.06
    SRC
    0.06
    rib
    0.06
    @register
    0.06
    /action
    0.06
    可
    0.06
     UPLOAD
    0.06
    .prepend
    0.06
    HR
    0.06
    Activations Density 0.028%

    No Known Activations