© 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. 89052
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    The neuron fires on question tokens—i.e. it detects when the text is asking a question.

    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
     Ils
    -0.07
     bikes
    -0.07
     copp
    -0.06
    amps
    -0.06
     Yine
    -0.06
     Dead
    -0.06
     rahat
    -0.06
    isis
    -0.06
     Nairobi
    -0.06
    個人
    -0.06
    POSITIVE LOGITS
     серпня
    0.07
    .invoice
    0.07
    Persistent
    0.07
    plements
    0.07
    productId
    0.07
    ΜΑ
    0.06
     히
    0.06
     khoản
    0.06
    谱
    0.06
    sms
    0.06
    Activations Density 0.008%

    No Known Activations