© 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. 110125
    Prev
    Next
    INDEX
    Explanations

    employment and purchasing

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs related to acquiring or exchanging goods (e.g. buy, rent, purchase).

    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
     tx
    -0.07
    bye
    -0.07
    damn
    -0.06
     constructing
    -0.06
     tre
    -0.06
    -friendly
    -0.06
    роме
    -0.06
    ті
    -0.06
     Play
    -0.06
    	btn
    -0.06
    POSITIVE LOGITS
    .habbo
    0.06
     mutated
    0.06
     προσ
    0.06
    하면
    0.06
     uzav
    0.06
     กระ
    0.06
     yiy
    0.06
    =username
    0.06
    。</
    0.06
     ου
    0.06
    Activations Density 0.062%

    No Known Activations