© 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. 7905
    Prev
    Next
    INDEX
    Explanations

    Young

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the word “young,” whether capitalized or not.

    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
    ref
    -0.08
    ريط
    -0.07
    /ref
    -0.06
    -control
    -0.06
     Alarm
    -0.06
     Brigade
    -0.06
    _minus
    -0.06
    ANJI
    -0.06
     ata
    -0.06
     avoir
    -0.06
    POSITIVE LOGITS
     Young
    0.16
     young
    0.16
    Young
    0.15
     Youth
    0.12
     younger
    0.11
     youth
    0.10
     genç
    0.10
    young
    0.10
     youngest
    0.09
     молод
    0.08
    Activations Density 0.020%

    No Known Activations