Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 118237
    Prev
    Next
    INDEX
    Explanations

    look

    np_max-act · gemini-2.0-flash

    verbs that indicate action or recommendation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the stock phrase “Take a look at” (i.e. the “Take a look…” invitation at the start of a sentence).

    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
    PLIT
    -0.06
    Cx
    -0.06
     özgür
    -0.06
     každé
    -0.06
     کد
    -0.06
    галі
    -0.06
    ーパ
    -0.06
     surtout
    -0.06
    �
    -0.06
    court
    -0.06
    POSITIVE LOGITS
    (elements
    0.07
     look
    0.06
     SEAL
    0.06
    (mask
    0.06
    ‌کنندگان
    0.06
    .quit
    0.06
    removeClass
    0.06
    кап
    0.06
     inside
    0.06
     Heck
    0.06
    Activations Density 0.011%

    No Known Activations