© 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. 41683
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    This neuron detects four‐digit year mentions (e.g. “2013,” “2009,” “2015”) in the text.

    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
    .Member
    -0.07
    SMART
    -0.06
    ematics
    -0.06
     ISSN
    -0.06
     дит
    -0.06
    decode
    -0.06
     EMP
    -0.06
    (coder
    -0.06
    igidbody
    -0.06
     STAT
    -0.06
    POSITIVE LOGITS
    弾
    0.08
    ATTLE
    0.07
    亮
    0.07
    ANGO
    0.06
    201
    0.06
    ган
    0.06
    تمع
    0.06
    屆
    0.06
     volta
    0.06
     اختلاف
    0.06
    Activations Density 0.018%

    No Known Activations